In the framework of the European/Japanese e-VITA project (https://www.e-vita.coach/),
IMT Atlantique is offering a one-year position in the field of active living technologies
(IoT, data fusion, AI, cloud/edge architectures, user services, coaching, NLP, etc.).

Description and link to apply:
https://institutminestelecom.recruitee.com/l/en/o/ingenieure-ou-ingenieur-en-fusion-multimodale-cdd-12-mois

Top

The Bordeaux Computer Science Laboratory (LaBRI) is currently looking to fill a 1 year post-doctoral position in the framework of the FVLLMONTI European project (http://www.fvllmonti.eu) 

Top

M2 internship offers LORIA - MULTISPEECH https ://team.inria.fr/multispeech/fr/

To apply, please send your CV and a short motivation letter directly to the supervisors of the

corresponding offer.

Offer 1 Contrastive Learning for Hate Speech Detection

General information Supervisors Nicolas Zampieri, Irina Illina, Dominique Fohr Address LORIA, Campus Scientifique - BP 239, 54506 Vandœuvre-lès-Nancy Phone 03 54 95 84 06 Email fistname.lastname@loria.fr Office C 145

Motivation and context The United Nations defines hate speech as 'any type of communication through speech, writing or behavior, which denigrates a person or group based on who they are, i.e. their religion, ethnicity, nationality, or other identity factor.'. We are interested in hate speech posted on social networks. With the expansion of social networks (Twitter, Facebook, etc.), the number of messages posted every day has increased dramatically. It is very difficult and expensive to process the millions of content posted every day in order to remove hateful content. Thus, automatic methods are required to moderate the influx. Automatic hate speech detection is a difficult task in the field of natural language processing (NLP) [6]. With the appearance of transformer-based language models like BERT [3], new state-of-the-art models have emerged for hate speech detection like HateBERT [1]. Current NLP models rely strongly on efficient learning algorithms. We are particularly interested in one of them : contrastive learning. Contrastive learning is employed to learn an embedding space such that pairs of similar sentences have close representations. [5] provide a summary of different models based on contrastive learning in language processing. Goals and Objectives The goal of this internship is to study contrastive learning in the context of hate speech detection. We believe that using this methodology will make the models more effective. Our model learns to estimate whether two sentences have the same sentiment or not. Based on the first model, the intern will explore other approaches of contrastive learning, such as SimCSE [4] or Dual Contrastive Learning [2] models. The studied methods will be validated on several datasets to assess the robustness of the approach. In our team, we have several labeled corpora from social networks. The internship workplan is as follows : at the beginning the student will conduct a state-of-the-art study on recent developments in hate speech detection and contrastive learning in NLP. The student will implement the selected methods. Finally, the performance of the different implemented methods will be evaluated on several hate speech corpora and compared to the state-of-the-art. Required Skills The candidate should have an experience with Deep Learning, including a good practice in Python and an understanding of deep learning libraries like Keras, Pytorch or Tensorflow. Additional information The student intern will join the MULTISPEECH team. The team provides access to the computational resources (GPU, CPU and datasets) in order to carry out the research.

References

[1] Caselli, T., Basile, V., Mitrovic, J., & Granitzer, M. HateBERT : Retraining BERT for Abusive Language ´ Detection in English.. Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021) (pp. 17-25). ACL. doi :10.18653/v1/2021.woah-1.3. August 2021. [2] Chen, Q., Zhang, R., Zheng, Y., & Mao, Y. Dual Contrastive Learning : Text Classification via Label-Aware Data Augmentation.. https ://arxiv.org/abs/2201.08702. 2022. 2 [3] Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. BERT : Pre-training of Deep Bidirectional Transformers for Language Understanding.. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics : Human Language Technologies, Volume 1 (Long and Short Papers), (pp. 4171-4186). 2022. [4] Gao, T., Yao, X., & Chen, D. SimCSE : Simple Contrastive Learning of Sentence Embeddings. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. ACL. doi :10.18653/v1/2021.emnlp-main.552. 2021. [5] Rethmeier, N., & Augenstein, I. A Primer on Contrastive Pretraining in Language Processing : Methods, Lessons Learned and Perspectives.. https ://arxiv.org/abs/2102.12982. 2021. [6] Zampieri, N., Ramishc, C., Illina, I., & Fohr D. Identification of Multiword Expressions in Tweets for Hate Speech Detection.. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 202-210, 2022. European Language Resources Association.

Offer 2 Diffusion-based Deep Generative Models for Audio-visual Speech Modeling

General information Supervisors Mostafa SADEGHI, Romain SERIZEL Address LORIA, Campus Scientifique - BP 239, 54506 Vandœuvre-lès-Nancy Email mostafa.sadeghi@inria.fr,romain.serizel@loria.fr

Motivation Recently, diffusion models have gained much attention due to their powerful generative modeling performance, in terms of both the diversity and quality of the generated samples [1]. It consists of two phases, where during the so-called forward diffusion process, input data are mapped into Gaussian noise by gradually perturbing the data. Then, during a reverse process, a denoising neural network is learned that removes the added noise at each step, starting from pure Gaussian noise, to eventually recover the original clean data. Diffusion models have found numerous successful applications, particularly in computer vision, e.g., text-conditioned image synthesis, outperforming previous generative models, including variational autoencoders (VAEs), generative adversarial networks (GANs), and normalizing flows (NFs). Diffusion models have also been successfully applied to audio and speech signals, e.g., for audio synthesis [2] and speech enhancement [3]. Goal and objectives Despite their rapid progress and application extension, diffusion models have not yet been applied to audiovisual speech modeling. This task involves joint modeling of audio and visual modalities, where the latter concerns the lip movements of the speaker, as there is a correlation between what is being said and the lip movements. This joint modeling effectively incorporates the complementary information of visual modality for speech generation. Such a framework has already been established based on VAEs [4]. Given the great potential and advantages of diffusion models, in this project, we would like to develop a diffusion-based audio-visual generative modeling framework, where the generation of audio modality, i.e., speech, is conditioned on the visual modality, i.e., lip images, similarly to text-conditioned image synthesis. This might then serve as an efficient representation learning framework for downstream tasks, e.g., audio-visual speech enhancement (AVSE) [4]. Background in statistical signal processing, computer vision, machine learning, and deep learning frameworks (Python, PyTorch) are favored. Interested candidates should send an email to the supervisors with a detailed CV and transcripts. Work environment This master internship is part of the REAVISE project : 'Robust and Efficient Deep Learning based Audiovisual Speech Enhancement' (2023-2026) funded by the French National Research Agency (ANR). The general objective of REAVISE is to develop a unified AVSE framework that leverages recent methodological breakthroughs in statistical signal processing, machine learning, and deep neural networks in order to design a robust and efficient AVSE framework. The intern will be supervised by Mostafa Sadeghi (researcher, Inria) and Romain Serizel (associate professor, University of Lorraine), as members of the MULTISPEECH team, and will benefit from the research environment, expertise, and computational resources (GPU & CPU) of the team.

References

[1] L. Yang, Z. Zhang, Y. Song, S. Hong, R. Xu, Y. Zhao, Y. Shao, W. Zhang, B. Cui, and M. H. Yang, Diffusion models : A comprehensive survey of methods and applications arXiv preprint arXiv :2209.00796, 2022. [2] Z. Kong, W. Ping, J. Huang, K. Zhao, and B. Catanzaro, Diffwave : A versatile diffusion model for audio synthesis arXiv preprint arXiv :2009.09761, 2020. [3] Y. J. Lu, Z. Q. Wang, S. Watanabe, A. Richard, C. Yu, and Y. Tsao, Conditional diffusion probabilistic model for speech enhancement IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022. [4] M. Sadeghi, S. Leglaive, X. Alameda-Pineda, L. Girin, and R. Horaud, Audio-visual speech enhancement using conditional variational auto-encoders IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 28, pp. 1788 ?1800, 2020. 

Offer 3 Efficient Attention-based Audio-visual Fusion Mechanisms for Speech Enhancement

General information Supervisors Mostafa SADEGHI Romain SERIZEL Address LORIA, Campus Scientifique - BP 239, 54506 Vandœuvre-lès-Nancy Email mostafa.sadeghi@inria.fr romain.serizel@loria.fr

Motivation Audiovisual speech enhancement (AVSE) is defined as the task of improving the quality and intelligibility of a noisy speech signal by utilizing the complementary information provided by the visual modality, i.e., lip movements of the speaker [1]. Visual modality is especially important in high-noise situations, as it is less affected by acoustic noise. Because of that, AVSE could be exploited in several practical applications, including hearing assistive devices. Numerous works have already studied the integration of visual modality with audio modality to improve the performance of speech enhancement. While the majority of audiovisual speech enhancement algorithms rely on deep neural networks and supervised learning, they require very large audiovisual datasets with diverse noise instances to have good generalization performance. A recently introduced AVSE approach is based on unsupervised learning [2,3], where during a training phase, the statistical distribution of clean speech is learned from a clean audiovisual dataset. This is done using a deep generative model, e.g. variational autoencoder (VAE) [4]. Then, at test (inference) time, the learned distribution is combined with a noise model to estimate the clean speech signal from the available noisy speech observations. Goal and objectives An important element of AVSE is audio-visual feature fusion, which should robustly and efficiently combine the two modalities. Current fusion mechanisms used for unsupervised AVSE are based on simple feature concatenation, which is not effective, as it treats the two feature streams on an equal basis. In fact, the audio modality usually contributes more than the visual modality, but in general, their contributions should be robustly balanced and weighted. In this project, we are going to develop efficient feature fusion modules based on attention models [5], which have proven very successful in different applications. The designed fusion module is supposed to robustly and efficiently incorporate the potentially different uncertainty (reliability) levels of the two modalities. We will then evaluate its effectiveness for AVSE. Background in statistical signal processing, probabilistic machine learning, optimization, and programming languages & deep learning frameworks (Python, PyTorch) are favored. Interested candidates should send an email to the supervisors with a detailed CV and transcripts. Work environment This master internship is part of the REAVISE project : 'Robust and Efficient Deep Learning based Audiovisual Speech Enhancement' (2023-2026) funded by the French National Research Agency (ANR). The general objective of REAVISE is to develop a unified AVSE framework that leverages recent methodological breakthroughs in statistical signal processing, machine learning, and deep neural networks in order to design a robust and efficient AVSE framework. The intern will be supervised by Mostafa Sadeghi (researcher, Inria) and Romain Serizel (associate professor, University of Lorraine), as members of the MULTISPEECH team, and will benefit from the research environment, expertise, and computational resources (GPU & CPU) of the team.

References

[1] D. Michelsanti, Z.-H. Tan, S.-X. Zhang, Y. Xu, M. Yu, D. Yu, and J. Jensen, An overview of deep-learningbased audio-visual speech enhancement and separation IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 29, pp. 1368 ?1396, 2021. 5 [2] M. Sadeghi and X. Alameda-Pineda, Switching variational auto-encoders for noise-agnostic audio-visual speech enhancement IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021. [3] M. Sadeghi, S. Leglaive, X. Alameda-Pineda, L. Girin, and R. Horaud, Audio-visual speech enhancement using conditional variational auto-encoders IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 28, pp. 1788 ?1800, 2020. [4] D. P. Kingma and M. Welling, An introduction to variational autoencoders Foundations and Trends in Machine Learning, 2019. [5] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, Attention is all you need Advances in neural information processing systems, 2017. 

Offer 4 Multi-modal Stuttering Detection Using Self-supervised Learning

General information Supervisors Shakeel Ahmad Sheikh, Slim Ouni Address LORIA, Campus Scientifique - BP 239, 54506 Vandœuvre-lès-Nancy Email fistname.lastname@loria.fr Office C 137

Motivation Stuttering is a neuro-developmental speech disorder that starts appearing when language, speech, and emotion supporting neural connections are changing quickly [2]. In standard stuttering therapy sessions, the speech pathologists or speech therapists either manually examine and analyze the person who stutter (PWS) speech or their recordings. In order to rectify the stuttering, the speech therapists carefully observe and monitor the patterns in speech utterances of PWS. However, this convention of stuttering detection is very time consuming and strenuous. It is also biased towards the subjective belief of speech language therapists. Thus, it is important to build stuttering detection interactive tools that provide impartial objective assessment, and can be utilized to tune and improve various ASR virtual assistants for stuttered speech. Deep learning has been used tremendously in domains like speech recognition [5], emotion detection [1], however, in stuttering domain, its application is limited. The acoustic cues embedded in the speech of PWS can be exploited by various deep learning methods in the detection of stuttering. Most of the existing stuttering detection techniques utilize spectral features such as spectrograms and MFCCs as an input representation of the stuttered speech [12, 11, 3]. The most common problem in the stuttering domain is the dataset issue. There are few stuttering datasets like UCLASS, FluencyBank, and SEP28K [3], which are small containing only a few dozens of speakers. While deep learning methods have shown substantial gains in domains like ASR, speaker verification, emotion detection, etc, however, the improvement in stuttering detection is very limited, most likely due to the miniature size of datasets. The common strategy in dealing with training on small datasets is to apply transfer learning, where the pre-trained model (trained first on some auxiliary task on a large dataset) is used to enhance the performance of the desired task, for which data is very scarce. The deep learning model trained on some auxiliary task can be fine-tuned by re-training, or replacing some of its last layers, or it can also be employed as a feature extractor for the desired task, that we are trying to address. Transfer learning methodology has been explored in various fields like ASR, emotion detection [8], etc. Recently, self-supervised learning has shown significant improvement in stuttering detection [11, 18, 17, 16]. Multimodal Stuttering Detection Stuttering can be characterized as an audio-visual problem. Cues are present both in the visual (e.g., head nodding, lip tremors, quick eye blinks, and unusual lip shapes) as well as in the audio modality [4]. This multimodal learning paradigm could be helpful in learning robust stutter-specific hidden representations across the cross-modality platform, and could also help in building robust automatic stuttering detection systems. Selfsupervised learning can also be exploited to capture acoustic stutter-specific representations based on guided video frames. As proposed by Shukla et al. [14], this framework could be helpful in learning stutter-specific features from audio signals guided by visual frames or vice versa. Altinkaya and Smeulders [15] recently presented the first audio-visual stuttered dataset which consists of 25 speakers (14 male, 11 female). They trained ResNet-based RNN (gated recurrent unit) on the audio-visual modality for the detection of block stuttering type. The main idea in this internship is to explore the impact of further self supervised learning in stuttering detection in combination with audio-visual setup. The goal of the proposed study is to develop and evaluate audio-visual based self supervised stuttering detection classifiers, that will be able to distinguish among several stutter classes. 1. Objective 1 : Lliterature survey by looking at the existing work in stuttering detection. 2. Objective 2 : Developing a pre-trained stuttering classifier based on self-supervised learning ; Some initial experiments would be carried out. We would explore the self supervised models such as wav2vec 2.0, a modified version of wav2vec [9], and their variants such as Unispeech, HuBERT, etc. We would use wav2vec 2.0 either as a feature extractor or just fine tune it by replacing the last few layers and adapt it for stuttering detection. 7 3. The experiments would be carried out on the newly developed French stuttering dataset. 4. Objective 3 : Carrying out the actual experiments and the impact of fine-tuning and pre-trained features would be analyzed on the raw stuttered embedded audio-visual stuttered samples.

References

[1] Mehmet Berkehan Ak Cay and Kaya Oguz L. Yang, Z. Zhang, Y. Song, S. Hong, R. Xu, Y. Zhao, Y. Shao, W. Zhang, B. Cui, and M. H. Yang, Speech emotion recognition : Emotional models, databases, features, preprocessing methods, supporting modalities, and classifiers' Speech Communication, 116 (2020) pp.56- 76. [2] Smith, Anne and Weber, Christine How stuttering develops : The multifactorial dynamic pathways theory' Journal of Speech, Language, and Hearing Research, 60 (2017) pp.2483–2505. [3] Shakeel A. Sheikh, Md Sahidullah, Fabrice Hirsch, Slim Ouni, Machine learning for stuttering identification : Review, challenges and future directions, Neurocomputing, 514 (2022), pp 385-402, [4] Guitar, Barry. Stuttering : An integrated approach to its nature and treatment. Lippincott Williams & Wilkins, 2013. [5] A. B. Nassif, I. Shahin, I. Attili, M. Azzeh and K. Shaalan, 'Speech Recognition Using Deep neural networks : A systematic review,' IEEE Access, vol. 7, pp. 19143-19165, 2019. [6] Latif, Siddique, Rajib Rana, Sara Khalifa, Raja Jurdak, Junaid Qadir, and Björn W. Schuller. 'Deep representation learning in speech processing : Challenges, recent advances, and future trends.' arXiv preprint arXiv :2001.00378 (2020). [7] Ning, Y., He, S., Wu, Z., Xing, C. and Zhang, L.J., 2019. A review of deep learning based speech synthesis. Applied Sciences, 9(19), p.4050. [8] Wang, Yingzhi, Abdelmoumene Boumadane, and Abdelwahab Heba. 'A fine-tuned wav2vec 2.0/hubert benchmark for speech emotion recognition, speaker verification and spoken language understanding.' arXiv preprint arXiv :2111.02735 (2021). [9] Baevski, Alexei, Yuhao Zhou, Abdelrahman Mohamed, and Michael Auli. 'wav2vec 2.0 : A framework for self-supervised learning of speech representations.' Advances in Neural Information Processing Systems, 33 (2020) : 12449-12460. [10] Lea, Colin, Vikramjit Mitra, Aparna Joshi, Sachin Kajarekar, and Jeffrey P. Bigham. 'Sep-28k : A dataset for stuttering event detection from podcasts with people who stutter.' In ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6798-6802. IEEE, 2021. [11] Sheikh, Shakeel A., Md Sahidullah, Slim Ouni, and Fabrice Hirsch. 'End-to-End and Self-supervised learning for ComParE 2022 stuttering sub-challenge.' In Proceedings of the 30th ACM International Conference on Multimedia, pp. 7104-7108. 2022. [12] Sheikh, Shakeel A., Md Sahidullah, Fabrice Hirsch, and Slim Ouni. 'Robust stuttering detection via multi-task and adversarial learning.' In 2022 30th European Signal Processing Conference (EUSIPCO), pp. 190-194. IEEE, 2022. [13] Ngiam, Jiquan, Aditya Khosla, Mingyu Kim, Juhan Nam, Honglak Lee, and Andrew Y. Ng. 'Multimodal deep learning.' In ICML. 2011. [14] Shukla, Abhinav, Konstantinos Vougioukas, Pingchuan Ma, Stavros Petridis, and Maja Pantic. 'Visually guided self supervised learning of speech representations.' In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6299-6303. IEEE, 2020. [15] Altinkaya, Mehmet, and Arnold WM Smeulders. 'A dynamic, self supervised, large scale audiovisual dataset for stuttered speech.' In Proceedings of the 1st International Workshop on Multimodal Conversational AI, pp. 9-13. 2020. [16] Mohapatra, Payal, Akash Pandey, Bashima Islam, and Qi Zhu. 'Speech disfluency detection with contextual representation and data distillation.' In Proceedings of the 1st ACM International Workshop on Intelligent Acoustic Systems and Applications, pp. 19-24. 2022. [17] Grósz, Tamás, Dejan Porjazovski, Yaroslav Getman, Sudarsana Kadiri, and Mikko Kurimo. 'Wav2vec2- based Paralinguistic Systems to Recognise Vocalised Emotions and Stuttering.' In Proceedings of the 30th ACM International Conference on Multimedia, pp. 7026-7029. 2022. [18] Bayerl, Sebastian P., Dominik Wagner, Elmar Nöth, and Korbinian Riedhammer. 'Detecting Dysfluencies in Stuttering Therapy Using wav2vec 2.0.' arXiv preprint arXiv :2204.03417 (2022).

Offer 5 Dictionary learning for deep unsupervised speech separation

General information Supervisors Paul Magron Mostafa Sadeghi Address LORIA, Campus Scientifique - BP 239, 54506 Vandœuvre-lès-Nancy Email paul.magron@inria.fr mostafa.sadeghi@inria.fr Office C 141 C 136

Motivation and context Speech separation consists in isolating the signals that correspond to each speaker from an acoustic mixture where several persons might be speaking. This task is an important preprocessing step in many applications such as hearing aids or vocal assistants based on automatic speech recognition. State-of-the-art separation systems rely on supervised deep learning, where a network is trained to predict the isolated speakers’ signals from their mixture [1, 2]. However, these approaches are costly in terms of training data and have a limited capacity to generalize to unseen speakers. Goal and objectives The goal of this internship is to design a fully unsupervised system for speech separation, which is more data-efficient than supervised approaches, and applicable to any mixture of speakers. To that end, we propose to combine variational autoencoders (VAEs) with dictionary models (DMs). DM consist in decomposing a given input matrix (usually : an audio spectrogram) as the product of two interpretable factors : a dictionary of spectra and a temporal activation matrix). This family of methods has been extensively researched before the era of deep learning [3], but it is limited since real-world audio spectrograms cannot be decomposed using such simple models. Therefore, we propose to leverage VAEs as a tool to learn a latent representation of the data which is regularized using DMs. Such a system can be cast as an instance of transform learning [4] : the key idea is to apply a (learned) transform to the data so that it better complies with a desirable property - here, decomposition on a dictionary. A first attempt was recently proposed and has shown promising results in terms of speech modeling [5], although it was using a fixed dictionary. This internship aims at extending this work by considering a system where both the VAE and the dictionary are learned jointly, and applying it to the task of speech separation. Once trained, the resulting system operates in three stages : (i) the (mixture) audio spectrogram is projected through the encoder into some latent space ; (ii) this latent representation is decomposed efficiently using a DM learning algorithm, which provides a latent feature for each speaker ; (iii) these latent features are passed through the decoder to retrieve a spectrogram for each speaker. Such a system is promising since it is fully unsupervised (it can be trained without knowledge of specific mixtures), it yields an interpretable decomposition of the latent representation, and it can serve as a basis for other applications (including speaker diarization, speech enhancement or voice conversion). A good practice in Python and basic knowledge about deep learning, both theoretical and practical (e.g., using PyTorch) are required. Some notions of audio/speech signal processing and machine learning is a plus. Work environment The trainee will be supervised by Paul Magron (Chargé de Recherche Inria) and Mostafa Sadeghi (Researcher, Inria Starting Faculty Position), and will benefit from the research environment and the expertise in audio signal processing of the MULTISPEECH team. This team includes many PhD students, post-docs, trainees, and permanent staff working in this field, and offers all the necessary computational resources (GPU and CPU, speech datasets) to conduct the proposed research. 

References

[1] D. Wang and J. Chen, Supervised Speech Separation Based on Deep Learning : An Overview IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 26, no. 10, pp. 1702-1726, 2018. [2] Y. Luo and N. Mesgarani, Conv-TasNet : Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 27, no. 8, pp. 1256- 1266, 2019. [3] T. Virtanen, Monaural Sound Source Separation by Nonnegative Matrix Factorization With Temporal Continuity and Sparseness Criteria IEEE Transactions on Audio, Speech, and Language Processing, vol. 15, no. 3, pp. 1066-1074, 2007. [4] D. Fagot, H. Wendt and C. Févotte, Nonnegative Matrix Factorization with Transform Learning IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018. [5] M. Sadeghi, and P. Magron, A Sparsity-promoting Dictionary Model for Variational Autoencoders Interspeech, 2022. 

Offer 6 Semantic latent space for expressive text-to-speech

General information Supervisors Vincent Colotte, Slim Ouni Address LORIA, Campus Scientifique - BP 239, 54506 Vandœuvre-lès-Nancy Phone 03 54 95 20 74 Email vincent.colotte@loria.fr, slim.ouni@inria.fr Office C141

Motivation Over the last decades, text-to-speech synthesis (TTS) has reached good quality and intelligibility, and is now commonly used in information delivery services, as for instance in call center automation, and in navigation systems. In the past, the main goal when developing TTS systems was to achieve high intelligibility. The speech style was then typically a “reading style,” which resulted from the style of the speech data used to develop TTS systems (reading of a large set of sentences). Recent research on speech synthesis focuses now on expressive speech to obtain generated speech more expressive or spontaneous. Almost all systems are now based on neural network methods. Therefore, to tackle expressiveness integration in a network, as numerous recent works in neural networks, training and testing step pass through several steps with specific latent spaces to condition the network or to propose a latent representation to control the expressiveness. In stochastic processes, the explanation of such a numeric representation is still difficult to extract [1]. Moreover, the use of new representations as Word2Vec for textual material or Wav2Vec for audio signal shows that we can find a representation with implicit linguistic and semantic information. The need of explanation still remains. The internship will take place in this framework. Objectives and expected outcomes The goal of the proposed study is to investigate the information contained in a latent representation dedicated to expressive speech. Previous work dealt with Variational Autoencoder (VAE) approach to explore this dimension in the audiovisual domain [2] without emotion tag the latent representation retrieved the emotional information. In addition, [3] used several representations of acoustic expressiveness to condition a network to transfer an emotion from a speaker to another sentence of another speaker. Moreover, [5] had jointly used acoustic and textual expressiveness representation. The textual representation was based on SBERT approach. The internship work will consist to analyze latent representations of a TTS system (for instance Glow approach for audio speech or VAE for audio-visual speech). The second step will introduce semantic information by textual latent representation from simple tag [4], a description or the text itself. The objective is to jointly learn representations and analyze them to extract understanding for controlling the system. Additional information and requirements The internship will be carried out within the framework of the European project Humane-AI-Net. A good knowledge of Python and basic knowledge of neural network learning is required.

References

[1] Tits, N., Wang, F., Haddad, K.E., Pagel, V., Dutoit, T. Visualization and interpretation of latent spaces for controlling expressive speech synthesis through audio analysis, in Proc. Interspeech, 2019 [2] S. Dahmani, V. Colotte, V. Girard and S. Ouni Learning emotions latent representation with CVAE for TextDriven Expressive AudioVisual Speech Synthesis, in Neural Networks, Elsevier, 2021 [3] A. Kulkarni, V. Colotte, D. Jouvet, Analysis of expressivity transfer in non-autoregressive end-to-end multispeaker TTS systems, in Proc. Interspeech, 2022 [4] Kim, M., Cheon, S.J., Choi, B.J., Kim, J.J., Kim, N.S. Expressive Text-to-Speech Using Style Tag. Interspeech 2021 [5] Shin, Y., Lee, Y., Jo, S., Hwang, Y., Kim, T., Text-driven Emotional Style Control and Cross-speaker Style Transfer in Neural TTS. Interspeech 2022. 

Offer 7 Disentanglement in Speech Data for Privacy Needs

General information Supervisors Emmanuel Vincent, Marc Tommasi Address LORIA, Campus Scientifique - BP 239, 54506 Vandœuvre-lès-Nancy Email emmanuel.vincent@inria.fr, marc.tommasi@inria.fr

Motivation and context Large-scale collection, storage, and processing of speech data poses severe privacy threats [1]. Indeed, speech encapsulates a wealth of personal data (e.g., age and gender, ethnic origin, personality traits, health and socioeconomic status, etc.) which can be linked to the speaker’s identity via metadata or via automatic speaker recognition. Speech data may also be used for voice spoofing using voice cloning software. With firm backing by privacy legislations such as the European general data protection regulation (GDPR), several initiatives are emerging to develop and evaluate privacy preservation solutions for speech technology. These include voice anonymization methods [2] which aim to conceal the speaker’s voice identity without degrading the utility for downstream tasks, and speaker re-identification attacks [3] which aim to assess the resulting privacy guarantees, e.g., in the scope of the VoicePrivacy challenge series [4]. Goals and objectives The internship will tackle the objective of speech anonymization. Previous works have shown that simple adversarial approaches that aim at removing speaker identity from speech signals do not provide sufficient privacy guaranties [5]. An interpretation of this failure can be that adversaries were not strong enough. Moreover, there is no clear evidence that a transformation that removes speaker identity is informative enough to allow the reconstruction of intelligible speech signals. These observations raise a classical trade-off between privacy and utility that is essential in many privacy preservation scenarios. Instead of trying to remove speaker information, another option is to replace it by another one. To do so, a sub-objective is to disentangle speech signals, that is to isolate speech features that contribute to the success of speaker identification. Disentanglement is understood in this project as the process of embedding voice data in a new representation where different types of information (speaker identity, linguistic content, or even traits like age, gender or ethnicity) are separated and associated with disjoint sets of features. Variational autoencoders are supposed to naturally support disentanglement [6]. Additionally, variational approaches can also be used to make attackers stronger by introducing more diversity. Those two ways of improving adversarial approaches for learning a private representation of speech will be investigated.

References

[1] A. Nautsch, A. Jimenez, A. Treiber, J. Kolberg, C. Jasserand, E. Kindt, H. Delgado, M. Todisco, M. A. Hmani, A. Mtibaa, M. A. Abdelraheem, A. Abad, F. Teixeira, M. Gomez-Barrero, D. Petrovska, G. Chollet, N. Evans, T. Schneider, J.-F. Bonastre, B. Raj, I. Trancoso, and C. Busch. Preserving privacy in speaker and speech characterisation, in Computer Speech and Language, 2019 [2] B. M. L. Srivastava, M. Maouche, M. Sahidullah, E. Vincent, A. Bellet, M. Tommasi, N. Tomashenko, X. Wang, and J. Yamagishi. Privacy and utility of x-vector based speaker anonymization, in IEEE/ACM Transactions on Audio, Speech and Language Processing, 30 :2383–2395, 2022. [3] B. M. L. Srivastava, N. Vauquier, M. Sahidullah, A. Bellet, M. Tommasi, and E. Vincent. Evaluating voice conversion-based privacy protection against informed attackers, in Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020. [4] N. Tomashenko, X. Wang, E. Vincent, J. Patino, B. M. L. Srivastava, P.-G. Noé, A. Nautsch, N. Evans, J. Yamagishi, B. O’Brien, A. Chanclu, J.-F. Bonastre, M. Todisco, and M. Maouche. The VoicePrivacy 2020 Challenge : Results and findings, Computer Speech and Language, 2022. [5] B. M. L. Srivastava, A. Bellet, M. Tommasi, and E. Vincent. Privacy-preserving adversarial representation learning in ASR : Reality or illusion ?, in Proc. Interspeech, 2019 [6] L. Girin, S. Leglaive, X. Bie, J. Diard, T. Hueber, and X. Alameda-Pineda. Dynamical Variational Autoencoders : A Comprehensive Review, in Foundations and Trends in Machine Learning, vol. 15, 2021 12

Top

--

Top

L’IUT de Lannion et l’ENSSAT à Lannion (22) recherchent chacun une enseignante-chercheuse ou un enseignant-chercheur sur contrat LRU à temps plein en Informatique pour le reste de l’année (jusque fin août 2023).
Les fonctions de ce poste sont similaires à celles d'un poste d'ATER et cela peut être une solution pour terminer une thèse ou pour préparer les concours de chercheurs et d'enseignants-chercheurs. 

Top

Research position on speaker and text anonymization for medical applications @DFKI, Berlin

We’re happy to announce a new research position in the field of speech- and text anonymization at German Research Center for Artificial Intelligence, Berlin, Germany. We’re looking for a full time Researcher or Junior Researcher level, and offer a 2 years contract with optional prolongation and PhD perspective.

The Speech and Language Technology Lab at DFKI Berlin is involved in numerous national as well as international research programmes and networks. We offer an interesting and flexible work environment as part of an innovative, international and enthusiastic team which coordinates and participates in national as well as European projects in the wider area of Language Technology.

Your tasks

• Research and development of methods for anonymization and fake-detection using text, speech, and semi-structural data from medical and fake-news application domains
• Research and development of methods for explainability, fairness, trustworthiness for above methods 
• Support of industrial and public scientific, research and development projects on national and international level ( BMBF, EU, etc.)
• Exchange and network with relevant stakeholder from science, industry, politics and civil society.

Your qualifications

• Masters degree (or equivalent qualification) in Computer Science, Computational Linguistics, Signal Processing or a related discipline 
• MA degree in the area of speech, NLP, AI, ML, xAI
• Good English or German language skills
• Confident appearance in an international working environment and high self-motivation
• Ability to work in a team, problem-solving and results-oriented

Your benefits

• A wide and interesting range of tasks and extensive development opportunities in a young and international team
• Contribution to trend-setting, innovative projects in the field of Language Technology and AI
• An innovative, agile and professional work environment
• An attractive workplace in the heart of Berlin with PhD perspective

The German Research Center for Artificial Intelligence (DFKI) is Germany's leading business-oriented research institution in the field of innovative software technologies based on artificial intelligence methods. In the international scientific community, DFKI ranks among the most recognized 'Centers of Excellence' and currently is the biggest research center worldwide in the area of Artificial Intelligence and its application in terms of number of employees and the volume of external funds. The DFKI cooperates closely with national and international companies.

DFKI encourages applications from people with disability; DFKI intends to increase the proportion of female employees in the field of science and encourages women to apply for this position.

Application deadline: Dec 23

More details and link: https://jobs.dfki.de/en/internal/vacancy/en-researcher-m-w-d-in-506968.html

Top

Offre de post-doc de 6 mois au GIPSA-lab, Grenoble, sur le contrôle gestuel temps-réel de l'intonation pour la suppléance vocale, dans le cadre du projet ANR GEPETO (Gestures and Pedagogy of Intonation).

Top

SPEECH

RESEARCHER (M/F)

AboutVivoka

Job's Requirements

• Youarepassionate,creative,andhaveacollaborativemindset.

• YouhaveaPh.D.in speechprocessingor machinelearningorarelatedarea.Oryou areanexceptional candidate holdingaMaster's degree andhaveastrong experience.

• YouarefamiliarwithrecentresearchinDeepLearningandhavetheknowledge and skills to implement algorithms fromresearch papers.

• Youhavehands-onexperiencebuildingMLsystemsforsignalprocessingorrelated fields.

• Youhaveastrongprogrammingbackgroundwith2+yearsofexperienceinanyof the following languages: Python or C++.

• Youhavetheabilitytoquicklylearnnewtechnologiesandsuccessfully implement them.

• Youhavegoodanalyticalandsyntheticalskills.

• Youhavegoodwritingskills.

• YouarefluentinEnglish.

• Youhaveexperience withoneor moreof thefollowinglibraries:PyTorch, TensorFlow.

• Youhavescientificpublications inleadingspeechorsignalprocessingconferences (likelnterspeech,ICASSP,ASRU,etc.)andjournals.

• Youmayhaveexperiencewithresearchordevelopmentforembedded/edge devices

The advantages of the job

• Youwillbepartofagrowingproject,andbeoneofitspillars.

• AtVivoka,autonomyandtrustareimportantvalues.

• Everydayisanewchallenge,youwillnotexperiencemonotony.

• Eachprojectisaninnovation,youevolveinacrazyandstimulatingenvironment.

• AtVivoka,wemakeeveryeffortforouremployeesandtheirwell-being.

• Youwillbelocatedin Metzwhichisstrategically locatednear the bordersof France, Luxembourg andGermany.

• Youwillhavecomplementaryhealthinsurancebenefits.

• Youwillhavecomplementarymonthly mealvouchers.

If you are interested in the position,

send your documents to

Top

NLPRESEARCHER(M/F)

AboutVivoka

Job’s Requirements

• Youarepassionate,creative,andhaveacollaborativemindset.

• Youhaveawillingnesstolearnnewtechnologiesandsuccessfullyimplementthem.

• YouhaveaPhD(or M.Sc.) inNLP,MachineLearning,DataScience,Computer Science ora related area,and have a strong experience in NLP/NLU/NLG.

• You have strongscientific publications in NLP conferences such as ACL,EMNLP, COLING,etc.

• YouhaveanadvancedunderstandingofNLP/NLU/NLG techniquesandpractical experienceinbuildingMLmodelsforNLP/NLU/NLG and/orconversationalagents.

• Youhaveexperienceinbothrapidprototypingandexperimentation.

• Youhaveastrongprogrammingbackgroundwith2+yearsof experienceinanyof the followinglanguages: Python(PyTorchor TensorFlow) or C++.

• Youhavegoodanalyticalandsyntheticalskills.

• Youhavegoodwritingskills.

• You havegoodcommunicationskillsinEnglish(Frenchisnotmandatory).

• Youareableto clearlycommunicateyourtechnicalfindingsto anon-technical team.

• Youmayhaveexperiencewithresearchordevelopmentforembedded/edge devices.

The advantages of the job

• Youwillbepartofagrowingproject,andbeoneof its pillars.

• AtVivoka,autonomyandtrustareimportantvalues.

• Everydayisanewchallenge,youwillnotexperience monotony.

• Eachprojectisaninnovation,youevolvein acrazyandstimulatingenvironment.

• AtVivoka,wemakeeveryeffortforouremployeesandtheirwell-being.

• Youwillbelocatedin Metzwhichisstrategically locatednear thebordersof France, Luxembourg andGermany.

• Youwillhavecomplementaryhealthinsurancebenefits.

• Youwillhavecomplementarymonthlymealvouchers.

If you are interested in the position,

send your documents to

Top

MACHINELEARNING ENGINEER (M/F)

AboutVivoka

Job's Requirements

• YouholdaMaster/EngineerdegreeorPhDinMachineLearningwithinterestin

R&D.

• Youkeepyourself up-to-date withtherecentmethods andtechniques in applied deep learning and machine learning.

• Youarecomfortablewithreadingscientificresearchpapersaswellasdiscussing and implementing them.

• YouhaveexpertisewithMachineLearningframeworkssuchasPyTorchand TensorFlow.

• YouhaveexcellentskillsinatleastPythonorC++.

• You'vealreadycreatedproductionreadycomplexmodels.

• Youmayhaveexperiencewithresearchordevelopmentforembedded/edge devices.

• Youhavegoodanalyticalandsyntheticalskills.

• Youareindependentinyourwork.

• Youarecapableofvulgarizingcomplextopicsandpresentingthemtoateam.

• YouhavegoodcommunicationskillsinEnglish(Frenchisnotmandatory).

The advantages of the job

• Youwillbepartofagrowingproject,andbeoneofitspillars.

• AtVivoka,autonomyandtrustareimportantvalues.

• Everydayisanewchallenge,youwillnot experiencemonotony.

• Eachprojectisaninnovation,youevolveinacrazyandstimulatingenvironment.

• AtVivoka,wemakeeveryeffortforouremployeesandtheirwell-being.

• Youwillbelocatedin Metzwhichisstrategically locatednear the bordersof France, Luxembourg andGermany.

• Youwillhavecomplementaryhealthinsurancebenefits.

• Youwillhavecomplementarymonthlymealvouchers.

If you are interested in the position,

send your documents to

Top

Faculty position (Associate professor, tenure position) at Telecom Paris in

Machine-Learning for Social Computing.

Telecom Paris has a  new permanent (tenure) faculty position (Associate Professor/ “Maître de conférences”) in the area of **machine learning for social computing**. Applicants from the following sub-research areas are welcome:

• Neural models for the recognition and generation of socio-emotional behaviors

• Natural language and speech processing

• Dialogue, conversational systems, and social robotics

• Reinforcement learning for dialogue

• Sentiment analysis in social interactions

• Bias and explainability in AI

• Model tractability, multi-task learning, meta-learning

Important Dates

• March 20th, 2023: closing date for applications

• April 20th, 2023: hearings of the preselected candidates

Context

Social Computing team  [1] -  S²A (machine learning, statistics and signal processing) group [2] - LTCI (laboratoire de traitement et communication de l’information) [3] - Telecom Paris [4] . 

Ecosystem

Telecom Paris [4] is a founding member of the Institut Polytechnique de Paris (IP Paris), a world-class scientific and technological institution. Located at the Plateau de Saclay close to Paris-Saclay University, this Institution is a partnership between Ecole Polytechnique, ENSTA Paris, ENSAE Paris, Télécom Paris, Télecom SudParis, with HEC as a key partner.

Regularly ranked as one of the best engineering schools in France, Télécom Paris is recognized for its excellent training, its very good employability rate with high salaries, its high-level research, and its very close proximity to companies. The THE (Times Higher Education) ranks Télécom Paris 2nd best French engineering school, 5th better French university, and  6th « best small university ». The newly created institution IP Paris was ranked in the top 50 best universities in the QS world university ranking.

In the context of the Institut Polytechnique de Paris, the activities in Data Science and AI of the team benefit from the center Hi!Paris (https://www.hi-paris.fr), offering seminars, workshops, and fundings through calls for project 

Main missions/Research activities

• Develop groundbreaking research in the field of machine learning applied to Social Computing, which includes: natural language and speech processing, dialogue, conversational systems, and social robotics, reinforcement learning for dialogue, sentiment analysis in social interactions, bias and explainability in AI, model tractability, multi-task learning, meta-learning

• Develop both academic and industrial collaborations on the same topic, including collaborative activities with other Telecom Paris research departments and teams (including social sciences researchers of economics and social sciences department [6]), and research contracts with industrial players

• Set up research grants and take part in national and international collaborative research projects

• Publish high-quality research work in leading journals and conferences

• Be an active member of the research community (serving on scientific committees and boards, organizing seminars, workshops, and special sessions...)

Main missions/Teaching activities

 Participate in teaching activities at Telecom Paris  and its partner academic institutions (as part of joint Master programs), especially in natural language processing, speech processing, machine learning, and Data Science, including life-long training programs (e.g. the local “Mastères Spécialisés”)

Candidate profile

 As a minimum requirement, the successful candidate will have:

• A Ph.D. degree

• A track record of research and publication in one or more of the following areas: conversational artificial intelligence, machine learning,  natural language processing, speech and signal processing, human-agent interactions, social robotics

•  Experience in teaching

• An international postdoctoral experience is welcome but not mandatory

• Excellent command of English

 NOTE:

The candidate does *not* need to speak French to apply, just to be willing to learn the language (teaching will be mostly given in English)

Other skills expected include:

•    Capacity to work in a team and develop good relationships with colleagues and peers

•    Excellent writing and pedagogical skills

More about the position

•    Place of work: Saclay (Paris outskirts)

 How to apply?

Applications must be submitted via one of the following websites:

French Version: 

https://institutminestelecom.recruitee.com/o/enseignantchercheur-en-machine-learning-pour-la-modelisation-des-comportements-socioemotionnels-a-telecom-paris-cdi 

English Version:

https://institutminestelecom.recruitee.com/l/en/o/enseignantchercheur-en-machine-learning-pour-la-modelisation-des-comportements-socioemotionnels-a-telecom-paris-cdi

Applicants should submit a single PDF file that includes:

- cover letter,

- curriculum vitae,

- statements of research and teaching interests (4 pages)

- three publications

- contact information for two references

Contacts:  == please do not hesitate to directly contact us before applying ==

Chloé Clavel (Coordinator of the Social Computing team)

Stéphan Clémençon (Head of the S²A group)

Florence d’Alché-Buc  (Head of the IDS department)

[1] https://www.telecom-paris.fr/en/research/laboratories/information-processing-and-communication-laboratory-ltci/research-teams/signal-statistics-learning/social-computing 

[2] https://www.telecom-paris.fr/en/research/laboratories/information-processing-and-communication-laboratory-ltci/research-teams/signal-statistics-learning 

[3] https://www.telecom-paris.fr/fr/lecole/departements-enseignement-recherche/image-donnees-signal  

[4] https://www.telecom-paris.fr/en/research/laboratories/information-processing-and-communication-laboratory-ltci 

[5] https://www.telecom-paris.fr/en/home 

[6] https://www.telecom-paris.fr/en/the-school/teaching-research-departments/economics-and-social-sciences

Top

UMRAE-INRIA

PROPOSITION DE STAGE 2022-2023

Sujet de stage

Nouveaux algorithmes pour le diagnostic acoustique de salle automatisé

Niveau recommandé

☒Master (M2) ☐Master (M1) ☐Ingénieur ☐Licence ☐Bac + 2

Compétences requises

Acoustique des salles, Méthodes d’optimisation, Traitement du signal, Apprentissage automatique

Des connaissances en Python, Matlab serait un plus.

Master 2 (acoustique, informatique, traitement du signal…)

Introduction générale

Les nuisances sonores sont citées comme première source de gêne par les populations et constituent un enjeu sanitaire et social important. Dans les bâtiments, la gêne est souvent liée à une mauvaise qualité acoustique des salles due à une réverbération trop importante (cantine, piscine, crèche…). Dans le cadre de la réhabilitation acoustique des salles, la proposition d’une solution nécessite une bonne connaissance des caractéristiques géométriques et acoustiques de l’existant. Pour estimer certains paramètres inconnus (ex : absorption d’un plafond inconnu), les acousticiens de terrain s’appuient sur des mesures in situ du champ sonore et sur des modèles acoustiques numériques (ou analytique) dont ils calent de façon itérative les paramètres de façon à retrouver la valeur du champ sonore mesurée. Le processus complet d’un diagnostic est donc long, coûteux et parfois imprécis selon les modèles utilisés. Face à ce constat, le développement de méthodes dites inversespermettant de remonter automatiquement aux paramètres acoustiques d’intérêt à partir de la mesure constituerait une percée majeure pour l’acoustique du bâtiment, ouvrant la voie au développement d’outils plus simples, plus rapides et plus fiables à destination des acousticiens.

Sujet

Notre sujet, portant sur le développement de méthodes inverses en acoustique du bâtiment via des méthodes d’optimisation, de traitement du signal audio et/ou d’apprentissage automatique vient compléter la palette d’outils de prévision de champ sonore déjà existant. Par ailleurs, il vient aussi rompre l’herméticité existante entre le monde de l’audio et celui de l’acoustique, se traduisant par des conférences et journaux distincts. Des travaux préliminaires conduits par l’UMRAE et l’Inria, basés sur la réponse impulsionnelle de la salle (RIR ou Room Impulse Response), ont clairement montré qu’une application directe des approches d’optimisation (ainsi que d’approches d’apprentissage automatique) existantes dans d’autres domaines ne pouvait suffire pour résoudre notre problème. Ces approches doivent être adaptées au cas spécifique de l’acoustique. A ce jour, pour des conditions idéalisées (microphones et sources omnidirectionnels, salle rectangulaire, absorption plutôt faible des parois…), nos travaux ont montré qu’il est possible de « retrouver » au sein de la RIR l’absorption des parois et de reconstruire la géométrie de la salle et ce, sans connaissance a priori sur la position de la source sonore, des microphones.

Le/la candidat(e), entouré(e) de ses encadrants, viendra en renfort de deux doctorants travaillant sur ces méthodes inverses. Pour cela, il/elle devra prendre en main l’une des méthodes d’optimisation déjà mises en place (algorithmes itératifs Ransac, Sliding Franck Wolfe, Méthode des solutions fondamentales, réseaux de neurones…) ainsi que le modèle théorique spécifiquement retenu pour ces travaux d’optimisation pouvant être exprimé dans le domaine temporel, de Fourier ou sur une décomposition en harmoniques sphériques.

Plusieurs pistes de travail sont ensuite possibles, suivant les affinités du candidat et après discussion avec ses encadrants. Il pourra s’intéresser au modèle théorique de référence, par exemple, en l’utilisant dans l’un des domaines (temporel, Fourier ou Harmoniques sphériques). Il pourra aussi chercher à l’améliorer en y intégrant par exemple la directivité des sources et microphones, ou la diffusion des parois. En parallèle, le candidat pourra aussi s’intéresser à affiner les méthodes d’optimisation retenues pour le cas de l’acoustique, voire de proposer un autre algorithme d’optimisation utilisé dans un autre domaine de la physique. Pour finir, afin de valider ses travaux, le candidat aura à sa disposition des RIRs simulées avec des outils numériques de référence, mais aussi des RIRs mesurées notamment dans le cadre d’un projet de recherche mené conjointement avec l’Institut de Recherche en Coordination Acoustique/Musique (IRCAM Paris).

Informations générales

Lieu et durée du stage

Le stage aura lieu à Strasbourg au sein des locaux du Cerema (11 rue Jean Mentelin – 67200 Straabourg). Le stage est prévu pour une durée de 4-6 mois.

Encadrants

Antoine Deleforge, Chargé de Recherche Inria, Equipe Multispeech, 615 rue du jardin botanique, 54600 Villiers lès Nancy.

Pour des raisons pratiques, Antoine Deleforge est physiquement au sein de l’agence de Strasbourg 2 jours par semaine.

https://members.loria.fr/ADeleforge/ ; https://team.inria.fr/multispeech/ ; https://www.inria.fr/fr

Cédric Foy, Chargé de Recherche UMRAE, Cerema, Univ. Gustave Eiffel, 11 rue Jean Menteli, 67200 Strasbourg

https://www.cerema.fr/fr ; https://www.umrae.fr/ ; https://twitter.com/umrae_lab

Bibliographie

T. Sprunck, K. Chahdi, C. Foy, E. Franck, A. Deleforge, Reconstruction de la forme d’une pièce par super-résolution à l’aide de réponses impulsionnelles, 16ème Congrès Français d'Acoustique, Marseille, France, 11-15 avr. 2022.

S. Dilungana, A. Deleforge, C. Foy, S. Faisan, Estimation jointe des profils d’absorption des parois d’une salle à partir de réponses impulsionnelles, 16ème Congrès Français d'Acoustique, Marseille, France, 11-15 avr. 2022.

S. Dilungana, A. Deleforge, C. Foy, S. Faisan, Geometry-Informed estimation of surface absorption profiles from impulses responses, Eusipco, 30th European Signal Processing Conference, Belgrade, Serbia, 2022.

T. Sprunck, Y. Privat, C. Foy, A. Deleforge, Gridless 3D Recovery if Images Sources from Room Impulse Responses, preprint, 2022, https://arxiv.org/abs/2208.14017

S. Dilungana, A. Deleforge, C. Foy, and S. Faisan, Learning-based estimation of individual absorption profiles from a single room impulse response with known positions of source, sensor and surfaces. In INTER-NOISE and NOISE-CON Congress and Conference Proceedings, vol. 263, No. 1, pp. 5623-5630, 2021.

https://jtav.ifsttar.fr/fileadmin/contributeurs/JTAV/2022/JTAV2022_foyetcoll.pdf

Top

The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. Is e buidheann carthannais a th’ ann an Oilthigh Dhùn Èideann, clàraichte an Alba, àireamh clàraidh SC005336.

Top

The GIPSA-lab, Grenoble, is offering a

Ph.D. Position in Cognitive Neuroscience

Senses of confidence and effort in sensorimotor adaptation

(speech and reaching) 

Application deadline: 31/12/22; Starting date: 1/04/23 at the latest

 

Context

Numerous studies have explored sensorimotor learning in hand movements and speech production. They showed how individuals adapt their gestures in a way that compensates partially for the perturbation induced on the visual, auditory or somatosensory feedback. Varying degrees of compensation were observed across individuals (1–3) – in particular for pathological populations (4,5), for different sensorimotor perturbations (e.g. pitch or formant shifted feedback (6,7)), different languages (8) or different tasks (e.g. including linguistic confusion or not) (9,10).

Scientific objectives

In complement to this existing literature (7,11), the current project aims at exploring in more detail the factors influencing this varying degree of compensation to a sensorimotor perturbation. We will explore, in particular, the hypothesis that it may be influenced by the relative attention and confidence given to our different sensory feedbacks (visual and proprioceptive feedbacks for hand movements, auditory and proprioceptive feedbacks for speech), and to the related sense of effort felt in the task.

To that goal, several experiments of both visuo-motor and audio-motor perturbation will be conducted (see Figure 1). In a first behavioral step, we will explore how the degree of arm or speech compensation varies with an increasing rotation of the visual feedback or an increasing pitch shift of the auditory feedback, how it is influenced by the location or the pitch level of the target, and how it may be affected by an increasing degree of visual blurring or auditory masking. We will pay attention, in particular, to possible reorganizations of the compensatory behavior, detected from discontinuities in the compensation/perturbation relationship. 

 

Depending on the candidate’s interests and/or funding opportunities, a second step will explore further the neural correlates of these compensatory mechanisms (12–16) and of their possible re-organization with an increasing level of perturbation, using fMRI neuro-imaging; or the second step of the project will explore the possible impairment of these mechanisms in people who stutter, who demonstrate reduced degrees of compensation to an auditory perturbation (17–20), reduced tactile sensibility of the oral cavity (21–23), and increased sense of effort (24).

 

Required skills 

We are searching for a highly motivated candidate with:

- a Master degree (M.Sc., M. Eng. or equivalent) in (neuro)cognitive sciences, computer science, or signal processing

- knowledge and interest in motor control, neurosciences and speech.
- good programming skills in Matlab, Python or R

- experimental skills and interests

Lab and supervision

The PhD candidate will be supervised by Maëva Garnier, Fabien Cignetti and Pascal Perrier, in collaboration between the GIPSA-lab and TIMC-IMAG in Grenoble. He/she will join the PCMD team of GIPSA-lab in Grenoble, composed of six PhD students and 12 researchers and engineers (http://www.gipsa-lab.grenoble-inp.fr/en/pcmd.php)

Application instructions

The application consists of a motivation letter, CV (with detailed list of courses related to computer science, signal processing, and neuro-cognitive science), names and contact details of two references, and transcripts of grades from under-graduate and graduate programs.

Contact

Maëva Garnier      Email:   maeva.garnier@gipsa-lab.fr                    Phone: (+33) 4 76 57 50 61

Fabien Cignetti     Email:   fabien.cignetti@univ-grenoble-alpes.fr   Phone: (+33) 4 76 63 71 10

Pascal Perrier       Email:   pascal.perrier@gipsa-lab.fr                    Phone: (+33) 4 76 57 48 25 

 

References

1.    Ghosh SS, Matthies ML, Maas E, Hanson A, Tiede M, Ménard L, et al. An investigation of the relation between sibilant production and somatosensory and auditory acuity. J Acoust Soc Am. 2010;128(5):3079–87.

2.    Villacorta VM, Perkell JS, Guenther FH. Sensorimotor adaptation to feedback perturbations of vowel acoustics and its relation to perception. J Acoust Soc Am. 2007;122(4):2306–19.

3.    Savariaux C, Perrier P. Compensation strategies for the perturbation of the rounded vowel [u] using a lip tube: A study of the control space in speech production. J Acoust Soc Am. 1995;98(5):2428–42.

4.    Loucks T, Chon H, Han W. Audiovocal integration in adults who stutter: Audiovocal integration in stuttering. Int J Lang Commun Disord. 2012 Jul;47(4):451–6.

5.    Mollaei F, Shiller DM, Baum SR, Gracco VL. Sensorimotor control of vocal pitch and formant frequencies in Parkinson’s disease. Brain Res. 2016;1646:269–77.

6.    Jones JA, Munhall KG. Perceptual calibration of F0 production: evidence from feedback perturbation. J Acoust Soc Am. 2000 Sep;108(3 Pt 1):1246–51.

7.    MacDonald EN, Goldberg R, Munhall KG. Compensations in response to real-time formant perturbations of different magnitudes. J Acoust Soc Am. 2010 Feb 1;127(2):1059–68.

8.    Mitsuya T, MacDonald EN, Purcell DW, Munhall KG. A cross-language study of compensation in response to real-time formant perturbation. J Acoust Soc Am. 2011;130(5):2978–86.

9.    Bourguignon NJ, Baum SR, Shiller DM. Lexical-perceptual integration influences sensorimotor adaptation in speech. Front Hum Neurosci. 2014;8:208.

10.  Frank AF. Integrating linguistic, motor, and perceptual information in language production. University of Rochester; 2011.

11.  Liu H, Larson CR. Effects of perturbation magnitude and voice F0 level on the pitch-shift reflex. :8.

12.  Behroozmand R, Korzyukov O, Sattler L, Larson CR. Opposing and following vocal responses to pitch-shifted auditory feedback: Evidence for different mechanisms of voice pitch control. J Acoust Soc Am. 2012 Oct;132(4):2468–77.

13.  Parkinson AL, Flagmeier SG, Manes JL, Larson CR, Rogers B, Robin DA. Understanding the neural mechanisms involved in sensory control of voice production. Neuroimage. 2012;61(1):314–22.

14.  Toyomura A, Fujii T, Kuriki S. Effect of external auditory pacing on the neural activity of stuttering speakers. NeuroImage. 2011 Aug 15;57(4):1507–16.

15.  Zarate JM, Wood S, Zatorre RJ. Neural networks involved in voluntary and involuntary vocal pitch regulation in experienced singers. Neuropsychologia. 2010;48(2):607–18.

16.  Zarate JM, Zatorre RJ. Experience-dependent neural substrates involved in vocal pitch regulation during singing. Neuroimage. 2008;40(4):1871–87.

17.  Kim KS, Daliri A, Flanagan JR, Max L. Dissociated Development of Speech and Limb Sensorimotor Learning in Stuttering: Speech Auditory-motor Learning is Impaired in Both Children and Adults Who Stutter. Neuroscience. 2020 Dec 15;451:1–21.

18.  Daliri A, Wieland EA, Cai S, Guenther FH, Chang SE. Auditory-motor adaptation is reduced in adults who stutter but not in children who stutter. Dev Sci. 2018;21(2):e12521.

19.  Cai S, Beal DS, Ghosh SS, Tiede MK, Guenther FH, Perkell JS. Weak Responses to Auditory Feedback Perturbation during Articulation in Persons Who Stutter: Evidence for Abnormal Auditory-Motor Transformation. Larson CR, editor. PLoS ONE. 2012 Jul 23;7(7):e41830.

20.  Sengupta R, Shah S, Gore K, Loucks T, Nasir SM. Anomaly in neural phase coherence accompanies reduced sensorimotor integration in adults who stutter. Neuropsychologia. 2016;93:242–50.

21.  De Nil LF, Abbs JH. Kinaesthetic acuity of stutterers for oral and non-oral movements. Brain. 1991;114(5):2145–58.

22.  Loucks TM, De Nil LF. Oral kinesthetic deficit in adults who stutter: a target-accuracy study. J Mot Behav. 2006;38(3):238–47.

23.  Loucks TMJ, De Nil LF. Oral kinesthetic deficit in stuttering evaluated by movement accuracy and tendon vibration. Speech Mot Control Norm Disord Speech. 2001;307–10.

24.  Ingham RJ, Warner A, Byrd A, Cotton J. Speech effort measurement and stuttering: Investigating the chorus reading effect. 2006;

25.  Caudrelier T, Rochet-Capellan A. Changes in speech production in response to formant perturbations: An overview of two decades of research. 2019. 

 

Top

Advanced Selective Mutal Learning for audio source separation

Master internship, Lille (France),

2022 Advisors — Nathan Souviraà-Labastie, R&D Engineer, PhD, nathan.souviraa-labastie@steelseries.com — Pierre Biret, R&D Engineer, pierre.biret@steelseries.com Company description About GN Group GN was founded 150 years ago with a truly innovative and global mindset. Today, we honour that legacy with world-leading expertise in the human ear, sound and video processing, wireless technology, miniaturization and collaborations with leading technology partners. GN’s solutions are marketed by the brands ReSound, Beltone, Interton, Jabra, BlueParrott, SteelSeries and FalCom in 100 countries. The GN Group employs 6,500 people and is listed on Nasdaq Copenhagen (GN.CO). About SteelSeries SteelSeries is the worldwide leader in gaming and esports peripherals focused on premium quality, innovation, and functionality. SteelSeries’ family of professional and gaming enthusiasts are the driving force behind the company and help influence, design, and craft every single accessory and the brand’s software ecosystem, SteelSeries GG. In 2020, SteelSeries acquired Nahimic, the leader in 3D sound solutions for gaming. We are currently looking for a machine learning / audio signal processing intern to join the R&D team of SteelSeries’ Software & Services Business Unit in our French office (former Nahimic R&D team). Internship subject Audio source separation consists in extracting the different sound sources present in an audio signal, in particular by estimating their frequency distributions and/or spatial positions. Many applications are possible from karaoke generation to speech denoising. In 2020, our separation approaches [1, 2] were equaling the state of the art [3, 4] on a music separation task. Since then our speech denoising product has hit the market [5] and the team continue to explore many tracks of improvements (see for instance the following project [6, 7]). Selective Mutual Learning (SML) Mutual learning (ML) [8] is a general idea related to knowledge distillation (KD) [9] where a group of untrained lightweight networks simultaneously learn and share knowledge to perform tasks together during training. The specificity of Selective Mutual Learning [10] is that the high-confidence predictions are used to guide the remaining network while the low-confidence predictions are ignored. This helps removing poor predictions of the networks during sharing knowledge. It can be noticed that the knowledge sharing is operated via loss functions that take into account the prediction of the other networks. The approach is simple and already shows benefits compared to KD and ML for boosting the performance of the networks for speech separation. Research axes The intern will be able to use existing internal trainsets and already implemented network architectures, which will facilitate drawing unbiased comparisons to our baseline approach. After re-implementing the SML approach, here is a list of possible axes of improvement of the SML approach : — tune the confidence factor (hyper-parameter c in [10]) to fit our speech denoising baseline (DNN and trainset) — extend and test the SML approach to more than 2 networks — adapt the SML loss formula to incorporate our internal loss (description upon request) 1 — additional tests with — new or already implemented networks : TasNet [11] ,E3net [12], DPRNN [13], transformer [1]) — various trainset (music separation , speech separation, ... ) Skills Who are we looking for ? Preparing an engineering degree or a master’s degree, you preferably have knowledge in the development and implementation of advanced machine learning algorithms. Digital audio signal processing skills is a plus. Whereas not mandatory, notions in the following additional various fields would be appreciated : Audio effects in general : compression, equalization, etc. - Statistics, probabilist approaches, optimization. - Programming language : Python, Pytorch, Keras, Tensorflow, Matlab. - Voice recognition, voice command. - Computer programming and development : Max/MSP, C/C++/C#. - Audio editing software : Audacity, Adobe Audition, etc. - Scientific publications and patent applications. - Fluent in English and French. - Demonstrate intellectual curiosity. Références [1] I. Alaoui Abdellaoui et N. Souviraà-Labastie. « Blending the attention mechanism in TasNet ». working paper or preprint. Nov. 2020. [2] E. Pierson Lancaster et N. Souviraà-Labastie. « A frugal approach to music source separation ». working paper or preprint. Nov. 2020. [3] F.-R. Stöter, A. Liutkus et N. Ito. « The 2018 signal separation evaluation campaign ». In : International Conference on Latent Variable Analysis and Signal Separation. Springer. 2018, p. 293-305. [4] N. Takahashi et Y. Mitsufuji. « Multi-scale Multi-band DenseNets for Audio Source Separation ». In : 2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA). 29 juin 2017. arXiv : 1706.09588. [5] ClearCast AI Noise Canceling - Promotion video. https : / / www . youtube . com / watch ? v = RD4eXKEw4Lg. [6] M. Vial et N. Souviraà-Labastie. Learning rate scheduling and gradient clipping for audio source separation. Rapp. tech. SteelSeries France, déc. 2022. [7] The torchcustoml rschedulersGitHubrepository. https : / / github . com / SteelSeries / torch _ custom_lr_schedulers. [8] Y. Zhang et al. « Deep mutual learning ». In : Proceedings of the IEEE conference on computer vision and pattern recognition. 2018, p. 4320-4328. [9] G. Hinton, O. Vinyals, J. Dean et al. « Distilling the knowledge in a neural network ». In : arXiv preprint arXiv :1503.02531 2.7 (2015). [10] H. M. Tan et al. « Selective Mutual Learning : An Efficient Approach for Single Channel Speech Separation ». In : ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE. 2022, p. 3678-3682. [11] Y. Luo et N. Mesgarani. « TasNet : time-domain audio separation network for real-time, singlechannel speech separation ». In : arXiv :1711.00541 [cs, eess] (1er nov. 2017). 4*. [12] M. Thakker et al. « Fast Real-time Personalized Speech Enhancement : End-to-End Enhancement Network (E3Net) and Knowledge Distillation ». In : arXiv preprint arXiv :2204.00771 (2022). [13] Y. Luo, Z. Chen et T. Yoshioka. « Dual-path rnn : efficient long sequence modeling for timedomain single-channel speech separation ». In : ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE. 2020, p. 46-50.

Top

Personalized speech enhancement Master internship, Lille (France), 2022

Advisors — Damien Granger, R&D Engineer, damien.granger@steelseries.com — Nathan Souviraà-Labastie, R&D Engineer, PhD, nathan.souviraa-labastie@steelseries.com — Lucas Dislaire, R&D Engineer, lucas.dislaire@steelseries.com Company description

About GN Group GN was founded 150 years ago with a truly innovative and global mindset. Today, we honour that legacy with world-leading expertise in the human ear, sound and video processing, wireless technology, miniaturization and collaborations with leading technology partners. GN’s solutions are marketed by the brands ReSound, Beltone, Interton, Jabra, BlueParrott, SteelSeries and FalCom in 100 countries. The GN Group employs 6,500 people and is listed on Nasdaq Copenhagen (GN.CO). About SteelSeries SteelSeries is the worldwide leader in gaming and esports peripherals focused on premium quality, innovation, and functionality. SteelSeries’ family of professional and gaming enthusiasts are the driving force behind the company and help influence, design, and craft every single accessory and the brand’s software ecosystem, SteelSeries GG. In 2020, SteelSeries acquired Nahimic, the leader in 3D sound solutions for gaming. We are currently looking for a machine learning / audio signal processing intern to join the R&D team of SteelSeries’ Software & Services Business Unit in our French office (former Nahimic R&D team). Internship subject Audio source separation consists in extracting the different sound sources present in an audio signal, in particular by estimating their frequency distributions and/or spatial positions. Many applications are possible from karaoke generation to speech denoising. In 2020, our separation approaches [1, 2] were equaling the state of the art [3, 4] on a music separation task. Since then our speech denoising product has hit the market [5] and the team continue to explore many tracks of improvements (see for instance the following project [6, 7]). Speech related audio source separation task Speech enhancement[8] or speech denoising usually refers to the task where the signal of interest is one intelligible speaker drown in additive noise. Speech separation [9] (sometime speaker separation) refers to the task of separately retrieving multiple unknown speakers usually not drown in additive noise. In the case of Personalized Speech Enhancement (also called target voice separation or target speaker extraction), the signal of interest is a speaker but a known speaker. This opens to (1) potentially better speech enhancement performances and also (2) focus on a particular speaker where speech enhancement would have kept all intelligible speakers. Personalized speech enhancement The research area is really recent and has just been added last year to the DNS challenge 1 [10]. VoiceFilter [11] seems to be the first article to tackle the problem of Personalized speech enhancement. 1. It can be noticed that the DNS challenge tasks [10] are defined as being real-time with a 40ms constraint on the latency (mainly composed of the look-ahead). 1 It uses two separately-trained neural networks : one discrimination network that produces speaker-specific embeddings from reference utterances of the target speaker ; and one “main” network, that performs the actual speech enhancement by taking as input both the corrupted utterance and the target speaker embeddings. The approach has now been outperformed, e.g., [12], while the two-step approach tends to prevail in the literature [13, 14, 15] : firstly one needs to learn a target speaker representation during an enrollment phase for instance by means of speaker embeddings, such as x-vectors or d-vectors [12], secondly incorporate this results in the neural network that will learn to extract this target speaker’s speech. However, it can be noticed that two steps does not necessarily means 2 networks, for instance a jointly trained 4-stage network is proposed in [15]. Axis of research The objective of the internship is to address one or several of the following targets : — Firstly, a baseline framework needs to be set up. It will require : — A dataset tailored for the task : the available datasets in the scientific community does not completely fulfill the requirements for SteelSeries products (description upon request). Conversely, our current datasets partly lacks speaker information. Hence, one would need to opt for the best solution or tradeoff combination. — A speaker embedding baseline with the assumption that the signal captured during the enrollment is “clean”, i.e. only contains the signal of interest (or at least with no second speaker). — A speech enhancement model with speaker embeddings. The intern could for instance re-use our implementation (currently without speaker embeddings) of E3net [14]. — Secondly, once a first baseline has been trained, the candidate could benchmark on different scenarii (signal-to-noise ratio during enrollment, signal ratio between speakers and effect of additional noise, various and mixed language). The Target Speaker Over-Suppression metric could potentially be used (description in [12]), as well as DNS standard metrics. This could lead the candidate to work on one of the following items to improve the baseline framework on its identified weaknesses : — Testing various speaker embeddings and ways or positions of integration into the networks — The separate training of the speaker-encoding network has been found to work better than joint training [16, 17, 15] (multi-task learning being often hard to tune). However, this would need to be reassessed with the final chosen architecture. — More effective enrollment strategies [18, 19] could be chosen and adapted to SteelSeries use cases. — Implementing loss functions suitable for the separation task (Step 2) could also be of interest, for instance following ideas in [20] or by adapting our internal loss. Skills Who are we looking for ? Preparing an engineering degree or a master’s degree, you preferably have knowledge in the development and implementation of advanced machine learning algorithms. Digital audio signal processing skills is a plus. Whereas not mandatory, notions in the following additional various fields would be appreciated : Audio effects in general : compression, equalization, etc. - Statistics, probabilist approaches, optimization. - Programming language : Python, Pytorch, Keras, Tensorflow, Matlab. - Voice recognition, voice command. - Computer programming and development : Max/MSP, C/C++/C#. - Audio editing software : Audacity, Adobe Audition, etc. - Scientific publications and patent applications. - Fluent in English and French. - Demonstrate intellectual curiosity. 2 Références [1] I. Alaoui Abdellaoui et N. Souviraà-Labastie. « Blending the attention mechanism in TasNet ». working paper or preprint. Nov. 2020. [2] E. Pierson Lancaster et N. Souviraà-Labastie. « A frugal approach to music source separation ». working paper or preprint. Nov. 2020. [3] F.-R. Stöter, A. Liutkus et N. Ito. « The 2018 signal separation evaluation campaign ». In : International Conference on Latent Variable Analysis and Signal Separation. Springer. 2018, p. 293-305. [4] N. Takahashi et Y. Mitsufuji. « Multi-scale Multi-band DenseNets for Audio Source Separation ». In : 2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA). 29 juin 2017. arXiv : 1706.09588. [5] ClearCast AI Noise Canceling - Promotion video. https : / / www . youtube . com / watch ? v = RD4eXKEw4Lg. [6] M. Vial et N. Souviraà-Labastie. Learning rate scheduling and gradient clipping for audio source separation. Rapp. tech. SteelSeries France, déc. 2022. [7] The torchcustoml rschedulersGitHubrepository. https : / / github . com / SteelSeries / torch _ custom_lr_schedulers. [8] DNS challenge on the paperswithcode website. https://paperswithcode.com/sota/speechenhancement-on-deep-noise-suppression. [9] Speech separation task referenced on the paperswithcode website. https://paperswithcode.com/ task/speech-separation. [10] H. Dubey et al. « Icassp 2022 deep noise suppression challenge ». In : ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE. 2022, p. 9271- 9275. [11] Q. Wang et al. « Voicefilter : Targeted voice separation by speaker-conditioned spectrogram masking ». In : arXiv preprint arXiv :1810.04826 (2018). [12] S. E. Eskimez et al. « Personalized speech enhancement : New models and comprehensive evaluation ». In : ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE. 2022, p. 356-360. [13] R. Giri et al. « Personalized percepnet : Real-time, low-complexity target voice separation and enhancement ». In : arXiv preprint arXiv :2106.04129 (2021). [14] M. Thakker et al. « Fast Real-time Personalized Speech Enhancement : End-to-End Enhancement Network (E3Net) and Knowledge Distillation ». In : arXiv preprint arXiv :2204.00771 (2022). [15] C. Xu et al. « Spex : Multi-scale time domain speaker extraction network ». In : IEEE/ACM transactions on audio, speech, and language processing 28 (2020), p. 1370-1384. [16] K. Žmolıková et al. « Learning speaker representation for neural network based multichannel speaker extraction ». In : 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). IEEE. 2017, p. 8-15. [17] M. Delcroix et al. « Single channel target speaker extraction and recognition with speaker beam ». In : 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE. 2018, p. 5554-5558. [18] H. Sato et al. « Strategies to Improve Robustness of Target Speech Extraction to Enrollment Variations ». In : arXiv preprint arXiv :2206.08174 (2022). [19] X. Liu, X. Li et J. Serrà. « Quantitative Evidence on Overlooked Aspects of Enrollment Speaker Embeddings for Target Speaker Separation ». In : arXiv preprint arXiv :2210.12635 (2022). [20] H. Taherian, S. E. Eskimez et T. Yoshioka. « Breaking the trade-off in personalized speech enhancement with cross-task knowledge distillation ». In : arXiv preprint arXiv :2211.02944 (2022).

Top

Real time speaker separation

Master internship, Lille (France), 2022

Advisors — Nathan Souviraà-Labastie, R&D Engineer, PhD, nathan.souviraa-labastie@steelseries.com — Damien Granger, R&D Engineer, damien.granger@steelseries.com Company description About GN Group GN was founded 150 years ago with a truly innovative and global mindset. Today, we honour that legacy with world-leading expertise in the human ear, sound and video processing, wireless technology, miniaturization and collaborations with leading technology partners. GN’s solutions are marketed by the brands ReSound, Beltone, Interton, Jabra, BlueParrott, SteelSeries and FalCom in 100 countries. The GN Group employs 6,500 people and is listed on Nasdaq Copenhagen (GN.CO). About SteelSeries SteelSeries is the worldwide leader in gaming and esports peripherals focused on premium quality, innovation, and functionality. SteelSeries’ family of professional and gaming enthusiasts are the driving force behind the company and help influence, design, and craft every single accessory and the brand’s software ecosystem, SteelSeries GG. In 2020, SteelSeries acquired Nahimic, the leader in 3D sound solutions for gaming. We are currently looking for a machine learning / audio signal processing intern to join the R&D team of SteelSeries’ Software & Services Business Unit in our French office (former Nahimic R&D team). Internship subject Audio source separation consists in extracting the different sound sources present in an audio signal, in particular by estimating their frequency distributions and/or spatial positions. Many applications are possible from karaoke generation to speech denoising. In 2020, our separation approaches [1, 2] were equaling the state of the art [3, 4] on a music separation task. Since then our speech denoising product has hit the market [5] and the team continue to explore many tracks of improvements (see for instance the following project [6, 7]). Real time speaker separation This internship targets speaker separation which is formalized in the scientific community as the task of separately retrieving a given number of speech/speaker signals from a monaural mixture signal. Most of the scientific challenges [8] compare offline (not real-time) approaches. The objective of the internship is to address the following targets (more or less ordered) : — Based on our current speech denoising trainsets, the candidate will create a trainset for the speaker separation task that match the same in-house requirement. Indeed, most of the available datasets in the scientific community lack quantity, audio quality of the groundtruths, high sampling rate, diversity of speakers/noise type. In addition, for the SteelSeries use cases, the overlap in time of the different speech sources might be lower than in the scenarii used by the scientific community and it statistical distribution will need to be well identified/defined. — Once our offline and online baseline algorithm have been trained on such a trainset, the candidate could benchmark on different scenarii (number of speaker, signal ratio between speakers, effect of additional noise, various and mixed languages) to potentially fulfill the weakness of the trainset. — The first subjective listening could bring the candidate to design complementary metrics, for instance representing false positive in speaker attribution or representating the statistics about the time needed by real-time DNN to correctly attribute a signal to the correct speaker after some silence. 1 — While all the above could be done using state-of-the-art loss functions, the candidate could also adapt our internal loss to be permutation invariant [9]. — The scientific community is very active in proposing new DNN architectures (offline [10, 8] and online [11, 12]. The candidate could also re-implement or propose her/his own architecture. In particular, a multi-task approach where the DNN also outputs the number of active speakers would be of great interest. Skills Who are we looking for ? Preparing an engineering degree or a master’s degree, you preferably have knowledge in the development and implementation of advanced machine learning algorithms. Digital audio signal processing skills is a plus. Whereas not mandatory, notions in the following additional various fields would be appreciated : Audio effects in general : compression, equalization, etc. - Statistics, probabilist approaches, optimization. - Programming language : Python, Pytorch, Keras, Tensorflow, Matlab. - Voice recognition, voice command. - Computer programming and development : Max/MSP, C/C++/C#. - Audio editing software : Audacity, Adobe Audition, etc. - Scientific publications and patent applications. - Fluent in English and French. - Demonstrate intellectual curiosity. Références [1] I. Alaoui Abdellaoui et N. Souviraà-Labastie. « Blending the attention mechanism in TasNet ». working paper or preprint. Nov. 2020. [2] E. Pierson Lancaster et N. Souviraà-Labastie. « A frugal approach to music source separation ». working paper or preprint. Nov. 2020. [3] F.-R. Stöter, A. Liutkus et N. Ito. « The 2018 signal separation evaluation campaign ». In : International Conference on Latent Variable Analysis and Signal Separation. Springer. 2018, p. 293-305. [4] N. Takahashi et Y. Mitsufuji. « Multi-scale Multi-band DenseNets for Audio Source Separation ». In : 2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA). 29 juin 2017. arXiv : 1706.09588. [5] ClearCast AI Noise Canceling - Promotion video. https : / / www . youtube . com / watch ? v = RD4eXKEw4Lg. [6] M. Vial et N. Souviraà-Labastie. Learning rate scheduling and gradient clipping for audio source separation. Rapp. tech. SteelSeries France, déc. 2022. [7] The torchcustoml rschedulersGitHubrepository. https : / / github . com / SteelSeries / torch _ custom_lr_schedulers. [8] Speech separation task referenced on the paperswithcode website. https://paperswithcode.com/ task/speech-separation. [9] X. Liu et J. Pons. « On permutation invariant training for speech source separation ». In : ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE. 2021, p. 6-10. [10] Music separation task referenced on the paperswithcode website. https://paperswithcode.com/ sota/music-source-separation-on-musdb18. [11] DNS challenge on the paperswithcode website. https://paperswithcode.com/sota/speechenhancement-on-deep-noise-suppression. [12] H. Dubey et al. « Icassp 2022 deep noise suppression challenge ». In : ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE. 2022, p. 9271-9275

Top

Audio detection for gaming

Master internship, Lille (France), 2022

Advisors — Damien Granger, R&D Engineer, damien.granger@steelseries.com — Nathan Souviraà-Labastie, R&D Engineer, PhD, nathan.souviraa-labastie@steelseries.com Company description About GN Group GN was founded 150 years ago with a truly innovative and global mindset. Today, we honour that legacy with world-leading expertise in the human ear, sound and video processing, wireless technology, miniaturization and collaborations with leading technology partners. GN’s solutions are marketed by the brands ReSound, Beltone, Interton, Jabra, BlueParrott, SteelSeries and FalCom in 100 countries. The GN Group employs 6,500 people and is listed on Nasdaq Copenhagen (GN.CO). About SteelSeries SteelSeries is the worldwide leader in gaming and esports peripherals focused on premium quality, innovation, and functionality. SteelSeries’ family of professional and gaming enthusiasts are the driving force behind the company and help influence, design, and craft every single accessory and the brand’s software ecosystem, SteelSeries GG. In 2020, SteelSeries acquired Nahimic, the leader in 3D sound solutions for gaming. We are currently looking for a machine learning / audio signal processing intern to join the R&D team of SteelSeries’ Software & Services Business Unit in our French office (former Nahimic R&D team). Internship subject This internship targets the detection of a known signal in an audio scene (containing multiple signals). For instance, some signs and feedbacks in video games are always the same audio signal while the rest of the audio scene is changing. The current internal implementation is based on a legacy state of the art music identification system [1, 2] The objective of the internship is to address one or multiple of the following targets : — Agnostic to the source type (speech, music, audio gaming event ...), indeed the current approach is designed for music — Enable the handling of shorter target signal — Robustness to various overlapping audio noise type from the audio scene — Robustness to level variation over time (in the case of moving audio sources) — Explore the effect of having multi-channel signals as input, summing the channels might help to identify moving sound but potentially with the drawback of lowering the signal-to-noise ratio — Improvement of the above-mentioned aspects by adapting the approach to the use of a smaller dictionary of target signals (not millions like in the case of musics) Machine learning is the expected track, and in particular, pre-trained and potentially overfitted audio representation (embeddings). Here is a short list of examples : — Attention-Based Audio Embeddings [3] — Autoencoder [4] — Contrastive learning [5, 6] 1 Skills Who are we looking for ? Preparing an engineering degree or a master’s degree, you preferably have knowledge in the development and implementation of advanced machine learning algorithms. Digital audio signal processing skills is a plus. Whereas not mandatory, notions in the following additional various fields would be appreciated : Audio effects in general : compression, equalization, etc. - Statistics, probabilist approaches, optimization. - Programming language : Python, Pytorch, Keras, Tensorflow, Matlab. - Voice recognition, voice command. - Computer programming and development : Max/MSP, C/C++/C#. - Audio editing software : Audacity, Adobe Audition, etc. - Scientific publications and patent applications. - Fluent in English and French. - Demonstrate intellectual curiosity. Références [1] A. Wang. « The Shazam music recognition service ». In : Communications of the ACM 49.8 (2006), p. 44-48. [2] A. Wang et al. « An industrial strength audio search algorithm. » In : Ismir. T. 2003. Washington, DC. 2003, p. 7-13. [3] A. Singh, K. Demuynck et V. Arora. « Attention-Based Audio Embeddings for Query-by-Example ». In : arXiv preprint arXiv :2210.08624 (2022). [4] A. Báez-Suárez et al. « SAMAF : Sequence-to-sequence Autoencoder Model for Audio Fingerprinting ». In : ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 16.2 (2020), p. 1-23. [5] X. Wu et H. Wang. « Asymmetric Contrastive Learning for Audio Fingerprinting ». In : IEEE Signal Processing Letters 29 (2022), p. 1873-1877. [6] Z. Yu et al. « Contrastive unsupervised learning for audio fingerprinting ». In : arXiv preprint arXiv :2010.13540 (2020).

Top

Creation of a speech synthesis model from spontaneous speech

Keywords:

Speech synthesis, spontaneous speech, low ressource languages, Nigerian Pidgin Context Nigerian Pidgin is a large but under-resourced language that increasingly serves as the primary vernacular language of Africa’s most populous country. Once stigmatized as a “broken” variety of English spoken only by the uneducated, Nigerian Pidgin is now a source of pride for many speakers who view it as a home-grown vehicle for communication. It transcends class and ethnicity, lacking the tribal associations of indigenous languages and the colonial baggage associated with English. The language can now be seen and heard in college campuses, houses of worship, advertisements, Nigerian expat communities, and even on a local branch of the British Broadcasting Channel.

Objectives

Despite Nigerian Pidgin’s growing prestige and a pool of speakers rivaling those of major languages like Turkish or Korean, the grammatical and intonational properties of the language are comparatively understudied. This internship is the extension of an ongoing research project aimed at better understanding its linguistic properties through the development and adaptation of NLP technologies. This research’s principal aim is to produce a natural-sounding text-tospeech (TTS) model that will allow researchers to conduct perception tests to determine how intonation influences the interpretation of meaning. Thanks partly to the recent explosion of neural network-based speech technologies, researchers can now produce high-quality synthesis from relatively simple datasets using models like TacoTron 2, complementing classical approaches such as those based on Hidden Markov Models. Specifically, the intern will assist in developing a text-to-speech platform trained on an existing database of Nigerian Pidgin recordings. In addition to producing natural-sounding speech, a central goal of this project will be to build a TTS model that will allow for the direct modification of intonational patterns via explicit parameters provided by researchers. The intern’s work will contribute to the exploration of the language’s melodic and tonal properties by allowing researchers to produce variations of novel utterances differing only by their intonational patterns.

Primary tasks

• Surveying existing TTS models and selecting the most suitable approach

• Training a model on a corpus of Nigerian Pidgin • Optimizing and evaluating the model

Profile

A second-year master’s student with:

• A solid background in machine learning (speech synthesis is a plus)

• Good academic writing skills in English

• An strong interest in language and linguistics

Sous la tutelle de : www.lisn.upsaclay.fr | Twitter @LisnLab | LinkedIn LisnLab Site Belvédère : Campus Universitaire Bâtiment 507 Rue du Belvédère – 91405 Orsay Cedex Site Plaine : Campus Universitaire bâtiment 650 Rue Raimond Castaing – 91190 Gif-sur-Yvette M2-CS-Intenship 2022-2023

Modalities

The internship will take place from March 2023 for 5 to 6 months at the LISN lab in the Sciences and Language Technologies department, as well as in the MoDyCo lab at Paris Nanterre University (primarily at the location of shortest commute).

• The LISN’s Belvédère site is located in the plateau de Saclay: University campus building 507, rue du Belvédère, 91400 Orsay.

• The MoDyCo lab is located at the Université Paris Ouest Nanterre La Défense: Bâtiment A, 200, avenue de la République – 92001 Nanterre. The candidate will be supervised by Emmett Strickland (MoDyCo) and Marc Evrard (LISN). Allowance under the official standards (service-public.fr).

To apply

Please send a CV and brief cover letter highlighting your interest in the project to the following: • Emmett Strickland (emmett.strickland@parisnanterre.fr) • Marc Evrard (marc.evrard@lisn.upsaclay.fr)

Further reading

1. Tan, X., Qin, T., Soong, F., & Liu, T. Y. (2021). A survey on neural speech synthesis. arXiv preprint arXiv:2106.15561. https://arxiv.org/abs/2106.15561

2. Ning, Y., He, S., Wu, Z., Xing, C., & Zhang, L. J. (2019). A Review of Deep Learning Based Speech Synthesis. Applied Sciences (2076-3417), 9(19). https://www.mdpi.com/2076- 3417/9/19/4050

3.Bigi, B., Caron, B., & Abiola, O. S. (2017). Developing resources for automated speech processing of the african language naija (nigerian pidgin). In 8th Language & Technology Conference: Human Language Technologies as a Challenge for Computer Science and Linguistics (pp. 441-445). https://hal.archives-ouvertes.fr/hal-01705707/document

Top

Study and development of a vocal force model

Keywords:

Machine learning, voice strength, speech processing, expressive speech

Context

The project aims to model the vocal force (VF) estimation on speech recordings. VF is defined as the sound pressure level (SPL in C-weighted decibels) measured in free field, one meter away in front of the speaker’s mouth (Liénard, 2019). This SPL is unfortunately lost in the vast majority of recordings, though the human ear is able to estimate this information thanks to the spectral differences produced by the variations in vocal effort induced by these VF values. A corpus presenting a pair of calibrated/uncalibrated signals will be used to build a model capable of estimating the original value of VF (in dBC). Collaborations under development will benefit and extend this effort by expanding the collected corpus and applying the resulting model to other tasks (e.g., expressive synthesis, Evrard et al., 2015).

Objectives

The initial aim will be to increase the variational characteristics of the uncalibrated signal from the pair provided in this corpus. In practice, it will be necessary to apply a series of degradations corresponding to the variations in distance and positioning of the speaker with respect to the microphone. Moreover, other processing will be applied, such as those typically used in post-production (compression, gate, etc.). A model will then have to be trained from this calibrated/uncalibrated pair to reproduce a reliable estimate of the original VF from any recording. Different neural architectures will be evaluated, from simple feedforward neural networks to those based on complex representations (e.g., CNN, LSTM). Different feature extraction methods will also be considered: raw, perceptually filtered (e.g., Mel) spectrums, as well as self-supervised model-based (e.g., Baevski et al., 2020).

Tasks

• Reviewing speech corpus augmentation techniques

• Surveying learning architectures: neural and self-supervised for processing audio pairs

• Augmentation of the corpus through the application of acoustic degradations

• Building a model of voice strength restoration from the signal pairs

• Presenting an objective evaluation of the model’s performance, as well as a subjective evaluation via perceptual experiments

Profile

A second-year master’s student with:

• A solid background in machine learning

• Good academic writing skills in English

• A strong interest in expressive speech

Sous la tutelle de : www.lisn.upsaclay.fr | Twitter @LisnLab | LinkedIn LisnLab Site Belvédère : Campus Universitaire Bâtiment 507 Rue du Belvédère – 91405 Orsay Cedex Site Plaine : Campus Universitaire bâtiment 650 Rue Raimond Castaing – 91190 Gif-sur-Yvette M2-CS-Internship 2022-2023

Modalities The internship will take place from March 2023 for 5 to 6 months in the Department of Language Sciences and Technologies at the LISN laboratory. The LISN Belvedere’s site is located on the plateau de Saclay: University campus, building 507, rue du Belvédère, 91400 Orsay. The candidate will be supervised by Marc Evrard and Albert Rilliard. Allowance according to official standards (service-public.fr).

How to apply

Please send a CV and brief cover letter highlighting your interest in the project to Marc Evrard (marc.evrard@lisn.upsaclay.fr).

References

1. Baevski, A., Zhou, Y., Mohamed, A., & Auli, M. (2020). Wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in Neural Information Processing Systems, 33, 12449-12460.

2. Evrard, M., Delalez, S., d’Alessandro, C., & Rilliard, A. (2015). Comparison of chironomic stylization versus statistical modeling of prosody for expressive speech synthesis. In Sixteenth Annual Conference of the International Speech Communication Association.

3. Liénard, J. S. (2019). Quantifying vocal effort from the shape of the one-third octave long-term-average spectrum of speech. The Journal of the Acoustical Society of America, 146(4), EL369-EL375.

Top

Two full-time Postdoctoral Research Fellows in automatic lyrics generation and automatic singing voice/speech evaluation.

You can find the detailed job descriptions here:

https://smcnus.comp.nus.edu.sg/postdoct_job_description_2022

Top

FORMULAIRE DE STAGE RECHERCHE Intitulé du  projet CAIBots: Conversational AI with teams of robots

Encadrants Prof. Fabrice Lefèvre

Descriptif du stage : L'objectif du stage consiste à étudier la mise en place d’un dispositif robotique permettant la simulation en « conditions réelles » des IA conversationnelles (CAI) vocales. Entraîner puis tester de l’IA conversationnelle (chatbots, systèmes de dialogue) est couteux et complexe, nous souhaitons grandement réduire cette difficulté en fournissant une solution robotique physique autonome pour apprendre et évaluer de nouveaux modules pour la CAI avant de les utiliser avec de vrais utilisateurs humains. Dans un premier temps, il s’agira principalement de tester des solutions existantes et clefs en main pour les éléments de la chaîne de traitement du langage parlé et de vérifier leur niveau de performance en configuration robot-robot. Ensuite une recherche vers des solutions embarquées sera menée. Elle devra permettre d’améliorer la latence du dispositif mais aussi d’assurer une meilleure protection des données personnelles (en ôtant la nécessité du passage par des clouds propriétaires). Globalement le système d'interaction vocal mis en place devra permettant une discussion ouverte entre un humain et une machine sur des sujets généraux. Le cas d’usage envisagé se positionne donc dans la logique du challenge Amazon Alexa (https://developer.amazon.com/alexaprize) : développer un bot pouvant entretenir une conversation pendant quelques minutes. Il sera donc nécessaire de prévoir aussi un utilisateur simulé pour permettre une interaction robot-robot autonome (le cas de conversations multiparties humains-robots pourra aussi être testé, sans être un objectif prioritaire du stage). Il s'agira d’initier le dispositif, c'est à dire de mettre en place les composants en configuration de base, mais illustrant les capacités potentielles pouvant être atteintes avec un temps de développement plus conséquent. Les solutions robotiques et logicielles entrevues pour ce travail sont, par exemple : robot Pepper, Google Cloud ASR, SpeechBrain, RASA et/ou des modèles pré-entraînés (BERT, GPT, BlenderBot…) ... Il s’agit principalement de plateformes open-source, assez complètes. Le travail consistera à mettre en œuvre rapidement un système réel afin de pouvoir le faire progresser en configuration robot-robot puis le tester avec un panel représentatif d'utilisateurs potentiels. Si un intérêt pour l'apprentissage automatique et le traitement de la langue naturelle est essentiel, il est aussi attendu du stagiaire de bonnes capacités en développement logiciel. Le stage sera une occasion d'acquérir des compétences en traitement automatique de la langue dans un contexte d'expérimentation en robotique embarquée. Plusieurs pistes pour une prolongation en thèse sont ouvertes. Durée du stage 6 mois Rémunération Environ 540€ / mois Thématique associée au stage Systèmes de dialogue humain-machine, reconnaissance et compréhension de parole, interface cognitive, robotique

Top

Sujet de stage de M2 : Décodage des signaux EEG à l’aide des méthodes d’apprentissage automatique

Contexte L’EEG (électroencéphalographie) est une technique non invasive, qui permet de mesurer l’activité électrique du cerveau à l’aide d’électrodes placées sur la tête. Ces électrodes enregistrent l’activité électrique causées par les neurones. Les données recueillies sont enregistrées et peuvent être, à l’aide des méthodes d’apprentissage automatique, utilisées à diverses fins comme par exemple : analyse, classification ou interface neuronale directe [Cao20]. Dans le cadre du traitement automatique du langage et de la parole, des premiers travaux, avec des résultats préliminaires, sont apparus récemment (e.g. classification EEG avec une approche par Transformer [Sun21], des données EEG issues de la lecture de phrases [Hollenstein18] ou encore dans le cadre de méthodes combinant l’utilisation d’EEG avec des techniques de traitement du langage pour la détection de préférences utilisateur [Gauba17]).

Objectif L’objectif de ce stage consiste à reconnaître automatiquement des caractères dans un premier temps, puis des mots isolés, énoncés oralement via les signaux EEG. Les différentes étapes du stage peuvent se résumer comme suit : 1. Prise en main du casque EEG Emotiv EPOC-X (https://www.emotiv.com/epoc-x/). 2. Mettre en place un protocole expérimental et collecter un corpus permettant la mise en place des expériences. 3. Evaluer et choisir des algorithmes d’apprentissage automatique pour reconnaitre les caractères et/ou mots isolés à partir des signaux EEG du corpus collecté dans le cadre du stage.

Profil du candidat L’étudiant.e doit être en dernière année de diplôme d’ingénieur ou en Master 2 d’informatique. Il ou elle doit posséder des notions de programmation, maîtriser l’environnement Linux et les méthodes standard d’apprentissage automatique. Durée du stage 6 mois de février à mars 2023.

Lieu du stage Le stage aura lieu au sein du Laboratoire Informatique d’Avignon (LIA) à Avignon Université ou au sein du Laboratoire des Sciences du Numérique de Nantes (LS2N) à l’Université de Nantes.

Gratification Le stage sera gratifié selon le montant horaire en vigueur au 01/01/2023, considérant une convention de stage de 35 heures par semaine (4,05 euros soit ≃550 €/mois).

Comment postuler ? Merci d’envoyer par email à Mickael Rouvier (mickael.rouvier@univavignon.fr) et Richard Dufour (richard.dufour@univ-nantes.fr) les documents suivants : 1) CV ; 2) relevé de notes (licence et master) et 3) lettre de motivation.

Bibliographie

[Cao20] Cao, Z. (2020). A review of artificial intelligence for EEG-based brain− computer interfaces and applications. Brain Science Advances, 6(3), 162-170.

[Gauba17] Gauba, H., Kumar, P., Roy, P. P., Singh, P., Dogra, D. P., & Raman, B. (2017). Prediction of advertisement preference by fusing EEG response and sentiment analysis. Neural Networks, 92, 77-88.

[Hollenstein18] Hollenstein, N., Rotsztejn, J., Troendle, M., Pedroni, A., Zhang, C., & Langer, N. (2018). ZuCo, a simultaneous EEG and eye-tracking resource for natural sentence reading. Scientific data, 5(1), 1-13.

[Sun21] Sun, J., Xie, J., & Zhou, H. (2021). EEG classification with transformer-based models. In 2021 IEEE 3rd Global Conference on Life Sciences and Technologies (LifeTech) (pp. 92-93).IEEE

Top

Ref 6581/22, Postdoctoral Research Fellow, MARCS Institute for Brain, Behaviour & Development

About Western

Western Sydney University is a modern, forward-thinking, research-led university, located at the heart of Australia’s fastest-growing and economically significant region, Western Sydney. Boasting 11 campuses – many in Western Sydney CBD locations – and more than 200,000 alumni, 49,500 students and 3,500 staff, the University has 14 Schools with an array of well-designed programs and degrees carefully structured to meet the demands of future industry. The University is ranked in the top two per cent of universities worldwide, and as a research leader, over 85 per cent of the University’s assessed research is rated at ‘World Standard’ or above.

About the Role The MARCS

Institute for Brain, Behaviour and Development is seeking to appoint a Postdoctoral Research Fellow to join the Brain Sciences research program at Western Sydney University. This two year Postdoctoral Research Fellow position is funded by an ARC Discovery grant, “Investigating the characteristics of older adults' conversation behaviour” awarded to Chief Investigators (CIs) Professor Chris Davis and Professor Jeesun Kim at the MARCS Institute for Brain, Behaviour and Development, Western Sydney University, in collaboration with Partner Investigators (PI) Emeritus Professor Valerie Hazan at University College London. This project will investigate the production and perception of naturalistic conversations by young and older adults. In particular, the interest is in probing individualised semantic processing. The aim of the project is to understand factors that affect the engagement of older adults in conversations. In this role you will work with the team to develop, pilot, and apply new methods for probing individual-specific semantic processing and on the collection of sensory, perceptual, cognitive and electrophysiological (EEG) data. You will also implement procedures for analysing the data. The successful applicant will work closely with the above investigators and the rest of the research team, conducting studies and participating in supervising and/or training PhD students, Research Assistants, Honours students, and interns enlisted into the project. For further information about the role please refer to the attached Position

Description.

This is a full time, 2 year fixed term contract. Located in the new Westmead Innovation Quarter (WIQ) – a visionary research, health, education and business hub located in the Westmead Health Precinct. About MARCS The MARCS Institute for Brain, Behaviour and Development is an interdisciplinary research institute of Western Sydney. The vision for the Institute is to optimise human interaction and wellbeing across the lifespan. To strive to solve the problems that matter most through the themes: sensing and perceiving, interacting with each other, and technologies for humans. Researchers in MARCS come from many disciplines including cognitive science, developmental psychology, language science, music science, cognitive neuroscience, and biomedical, electrical, electronic and software engineering. Further information is available from our website - http://www.westernsydney.edu.au/marcs

About You

You will hold a relevant doctoral qualification, or substantial progress toward a PhD in Psychology, Cognitive Neuroscience, Computational linguistics or a related discipline. You must have experience in conducting neuroimaging and behavioural experiments.

Culture

Western Sydney University highly values equity and inclusiveness. We have a proud history of doing so and consider this an important part of our social and civic responsibilities as a University. We strive to contribute to tackling inequalities and promoting wellbeing within our own institution, the Greater Western Sydney region, nationally and internationally.

Remuneration Package:

Academic Level A: $103,304 to $124,808 p.a. (comprising Salary of $87,293 to $105,464 p.a., plus Superannuation and Leave Loading) Academic Level B: $131,136 to $154,738 p.a. (comprising Salary of $110,811 to $130,846 p.a., plus Superannuation and Leave Loading) Position Enquiries: Please contact Professor Chris Davis via email at chris.davis@westernsydney.edu.au

Closing Date:

8:30pm AEDT, Sunday, 12 February 2023

Immigration Sponsorship: Employer Visa sponsorship will be provided if required. Click here to view Position Description How to Apply: · Start your application by clicking the 'begin' button. · Login to an existing account or reset your password · Preview Application Form Western Sydney University is committed to diversity and social inclusion. Applications from people of culturally and linguistically diverse backgrounds; equity target groups including women, people with disabilities, people who identify as LGBTIQ, and people of Aboriginal and Torres Strait Islander descent are encouraged.

Professor Chris Davis, PhD

The MARCS Institute for Brain, Behaviour and Development

Western Sydney University

Westmead Innovation Quarter

Building U, Level 4

160 Hawkesbury Road (Corner of Farmhouse Road)

Westmead NSW 2145

 <chris.davis@westernsydney.edu.au>

Top

Senior Postdoctoral Position in SLP

University of Cambridge, Department of Engineering (UK)

The ALTA Institute is looking for a senior postdoctoral researcher in spoken language processing to join our research team investigating L2 English speaking automated assessment and learning.

Website: https://www.jobs.cam.ac.uk/job/39114/

Postdoctoral Position in SLP

University of Cambridge, Department of Engineering (UK)

The ALTA Institute is looking for a postdoctoral researcher in spoken language processing to join our research team investigating L2 English speaking automated assessment and learning.

Website:  https://www.jobs.cam.ac.uk/job/39023/

Top

Creation of a speech synthesis model from spontaneous speech

Keywords: Machine learning, speech synthesis, low resource languages, Nigerian Pidgin

Objectives The main aim is to produce a natural-sounding text-to-speech (TTS) model allowing to perform perceptual tests for experimental linguistics. Thanks partly to the recent evolution of neural network-based speech technologies, researchers can now produce high-quality synthesis from relatively simple datasets using models like TacoTron 2, complementing classical approaches such as those based on Hidden Markov Models. Specifically, the intern will assist in developing a text-to-speech platform trained on an existing database of Nigerian Pidgin recordings. In addition to producing natural-sounding speech, a central goal of this project will be to build a TTS model that will allow for the direct modification of intonational patterns via explicit parameters provided by researchers. The intern’s work will contribute to the exploration of the language’s melodic and tonal properties by allowing researchers to produce variations of novel utterances differing only by their intonational patterns. Context This work is part of a larger project to study Nigerian Pidgin. It is a large but under-resourced language that increasingly serves as the primary vernacular language of Africa’s most populous country. Once stigmatized as a “broken” variety of English spoken only by the uneducated, Nigerian Pidgin is now a source of pride for many speakers who view it as a home-grown vehicle for communication. It transcends class and ethnicity, lacking the tribal associations of indigenous languages and the colonial baggage associated with English. The language can now be seen and heard in college campuses, houses of worship, advertisements, Nigerian expat communities, and even on a local branch of the BBC.

Primary tasks

• Surveying existing TTS models and selecting the most suitable approach

• Training a model on a corpus of Nigerian Pidgin

• Optimizing and evaluating the model Profile

A second-year master’s student with:

• A solid background in machine learning (speech synthesis is a plus)

• Good academic writing skills in English • An strong interest in language and linguistics

Top

Nantes Université ouvre un poste de maître de conférences en informatique pour septembre 2023. L'enseignement sera effectué au sein de la Faculté des Langues et Cultures Etrangères (FLCE) et la recherche sera menée au sein du LS2N (Laboratoire des Sciences du numérique de Nantes).

Plusieurs profils de recherche sont possibles, dont celui du traitement automatique de données langagières, pour une intégration dans l'équipe TALN (Traitement Automatique du Langage Naturel).
Plus d'informations sur l'équipe sont disponibles en ligne (http://taln.ls2n.fr).

Top

Technische Universität Darmstadt is one of Germany’s leading technical universities with broad excellence in research, an interdisciplinary profile, and an explicit focus on engineering sciences.

The department of Electrical Engineering and Information Technology invites applications for a

Full Professorship (W3) or Assistant Professorship (W2 with Tenure Track) for Signal Theory and Statistical Learning (Code No 6)

We are looking for an excellent researcher with credentials in at least one of the following areas: •Theory and methods of statistical inference •Robust statistical signal processing • Statistical learning theory •Theoretical performance analysis and interpretability of signal processing methods •Guarantees and interpretability of statistical learning methods •New trends in statistical signal and learning theory Application deadline: March 15, 2023 All further information about the position and application process can be found under:

https://www.tu-darmstadt.de/universitaet/karriere_an_der_tu/stellenangebote/aktuelle_stellenangebote/stellenausschreibungen_detailansichten_1_502208.en.jsp

Top

L'Université Paris-Saclay recrute un·e Maître·sse de Conférences en informatique (27ème section) pour la rentrée 2023. La personne recrutée travaillera au LISN, le Laboratoire Interdisciplinaire des Sciences du Numériques de l'Université Paris-Saclay, dans le département Science et Technologies des Langues (STL). Le profil recherche porte sur le traitement la langue multimodale. L'enseignement se fera à l'UFR de Sciences.

N'hésitez pas à me contacter ou à contacter un membre du département Science et Technologies des Langues si vous avez des questions. Vous trouverez ci-dessous des détails sur les profils recherche et enseignement.

Cordialement,

Gilles Adda

-- 

|Depuis le 1er janvier 2021, le LIMSI a fusionné avec le LRI et est devenu le LISN (Laboratoire Interdisciplinaire des Sciences du Numérique)
|Since January 1st 2021, LIMSI merged with the LRI lab and became the LISN (Interdisciplinary Computer Science Laboratory)
|
- 
|
|Gilles Adda
|  responsable du département Sciences et Technologies des Langues
|  head of Language Science and Technology Department
|  http://www.limsi.fr/Individu/gadda/
|

Top

Stockholm

Ref. No. SU FV-0793-23

Closing date: 15/04/2023

URL to this page
https://www.su.se/english/about-the-university/work-at-su/available-jobs/phd-student-positions-1.507588?rmpage=job&rmjob=20262&rmlang=UK

Top

We have  currently 2 open postdoc position at the LISN (ex-LIMS). You can apply online
and get more details here:
- multilingual ASR
https://emploi.cnrs.fr/Offres/CDD/UMR9015-LUCOND-003/Default.aspx?lang=EN
- ASR for low computational resource environment
https://emploi.cnrs.fr/Offres/CDD/UMR9015-LUCOND-002/Default.aspx?lang=EN

Feel free to contact me if you have any questions.

Top

Le service Plateformes du laboratoire GIPSA-LAB (CNRS/G-INP/UGA, Grenoble) recrute un.e ingénieur.e d?étude en instrumentation.
Il/Elle interviendra en support pour les plateformes expérimentales du laboratoire, et en particulier celles en lien avec l'aéro-acoustique, l'automatique ou la robotique. Il/elle aura notamment en charge  la responsabilité technique de la plateforme AERO, dédiée à l'étude des phénomènes aéro-acoustiques de la production de parole : réalisation de l'interfaçage d'instrumentations, gestion et entretien du parc d'appareils de mesures, préparation et participation aux expériences scientifiques.

Pour plus d'information, la fiche de poste détaillée est disponible ici : https://filesender.renater.fr/?s=download&token=2ae39938-121d-44c4-b6ce-385029ecf331

N'hésitez pas à me contacter si besoin d'information complémentaire.

Coriandre VILAIN

-- 
Coriandre Vilain
Ingénieur de Recherche UGA
Equipe PCMD, Pôle Parole & Cognition, GIPSA-LAB 
--
Responsable Service Plateformes GIPSA
--
04 76 82 77 80
www.gipsa-lab.fr/~coriandre.vilain

Top

Dear All,

Telecom SudParis welcomes applications for a permanent position of Associate-Assistant Professor in artificial intelligence for semantic and multi-modal multimedia analysis. Telecom SudParis is a public graduate school for engineering, which has been recognized on the highest level in the domain of digital technology. Telecom SudParis is co-founder member of the Institut Polytechnique de Paris and part of the Institut Mines-Telecom, the number one group of engineering schools in France. The recruited assistant/associate professor will join the ARTEMIS (Advanced Research and TEchniques for Multidimensional Imaging Systems) Department of Télécom SudParis and the SAMOVAR laboratory. The targeted research theme concerns the field of artificial intelligence, applied to the semantic analysis of massive, distributed and heterogeneous multimedia data. This concerns the automatic, multi-modal interpretation of complex audio-visual documents, computer vision, multimedia indexation, knowledge extraction and machine learning methodologies. The expected contributions will focus on deep neural network learning methods and target the entire multimedia content processing chain. Detailed information can be found at the following URL: https://institutminestelecom.recruitee.com/l/en/o/maitre-de-conferences-en-intelligence-artificielle-pour-lanalyse-semantique-de-donnees-multimedia-cdi The application deadline is March 31, 2023. Please do not hesitate to contact me for any further information.

Best regards,

Titus ZAHARIA, Professor

Head of the ARTEMIS Department Télécom SudParis

Institut Polytechnique de Paris

titus.zaharia@telecom-sudparis.eu

Top

Title of Project: Deep Cascaded Representation Learning for Speech Modelling

Supervisor:Professor Thomas Hain

Deadline for Applications:13th April 2023

The LivePerson Centre for Speech and Language offers a 3 year fully funded PhD studentship
covering standard maintenance, fees and travel support, to work on cascaded deep learning structures
to model speech. The Centre is connected with the Speech and Hearing (SpandH) and the Natural
Language Processing (NLP) research groups in the Department of Computer Science at the University
of Sheffield.
Auto-encoding is a powerful concept that allows us to compress signals and find essential
representations.Th econcept was expanded to include context, which is usually referred to as
self-supervised learning. On very large amounts of speech data this has led to very successful
methods and models for representing speech data, for a wide range of downstream processes.
Examples of such models are Wave2Vec or WaveLM. Use of their representations often requires
fine-tuning to a specific task, with small amounts of data. When encoding speech, it is desirable to
represent a range of attributes at different temporal specificity. Such attributes often reflect a hierarchy
of information.
The aim in this PhD project is to explore the use of knowledge about natural hierarchies in speech in
cascaded auto- and contextual encoder/decoder models. The objective is to describe a structured way
to understand such hierarchies. The successful candidate is expected to propose methods to combine
different kinds of supervision (auto, context, label) and build hierarchies of embeddings extractions.
These propositions may have to be seen in the context of data availability and complexity. All
proposals are to be implemented and tested on speech data. Experiments should be conducted on a
range of speech data sets with different speech types and data set size.
The student will join a world-leading team of researchers in speech and language technology. The
LivePerson Centre for Speech and Language Technology was established in 2017 with the aim to
conduct research into novel methods for speech recognition and general speech processing, including
end to end modelling, direct waveform modelling and new approaches to modelling of acoustics and
language. It has recently extended its research remit to spoken and written dialogue. The Centre hosts
severa lResearch Associates, PhD researchers,graduate and undergraduate project students,
Researchers and Engineers from LivePerson, and academic visitors. Being fully connected with
SpandH brings collaboration, and access to a wide range of academic research and opportunities for
collaboration inside and outside of the University. The Centre has access to extensive dedicated
computing resources (GPU, large storage) and local storage of over 60TB of raw speech data.

The successful applicant will work under the supervision of Prof. Hain who is the Director of the
LivePerson Centre and also Head of the SpandH research group. SpandH was and is involved in a
large number of national and international projects funded by national bodies and EU sources as well
as industry. Prof. Hain also leads the UKRI Centre for Doctoral Training In Speech and Language
Technologies and their Applications (https://slt-cdt.ac.uk/) - a collaboration between the NLP research
group and SpandH. Jointly, NLP and SpandH host more than 110 active researchers in these fields.
This project will start as soon as possible.
If English is not your first language, you must have an IELTS score of 6.5 overall, with no less than 6.0
in each component.

How to Apply:All applications must be made directly to the University of Sheffield using the
Postgraduate Online Application Form.
Information on what documents are required and a link to the application form can
be found here - https://www.sheffield.ac.uk/postgraduate/phd/apply/applying
On your application, please name Prof. Thomas Hain as your proposed supervisor
and include the title of the studentship you wish to apply for.
Your research proposal should:
●Be no longer than 4 A4 pages, including references
●Outline your reasons for applying for this studentship
●Explain how you would approach the research, including details of your
skills and experience in the topic area
If you have any queries, please contact phd-compsci@sheffield.ac.uk

Funding Details:
This position is fully funded by LivePerson, covering all tuition fees and a stipend at
the standard UKRI rate

Top

Job Title:Research Associate in Integrated Multitask Neural Speech Labelling
For further information and the link to apply please visit:
https://www.jobs.ac.uk/job/CXH168/research-associate-in-integrated-multitask-neural-speech-
labelling
Deadline for
Applications:15th March 2023
We are seeking an outstanding Research Associate in Integrated Multitask Neural Speech
Labelling, to join the LivePerson Centre for Speech and Language Technology based at the
University of Sheffield, which is linked with the Speech and Hearing (SpandH) research group
in the Department of Computer Science.
Youare applying to join a world-leading team of researchers in speech and language
technology to work on new ways to integrate a variety of speech technology labelling,
clustering or segmentatio ntasks into a single algorithm or process, in the context o fdeep
neural networks.Even end to end(E2E) automatic speech recognition is  typically
considered as a standalone process, independent of other speech audio technology tasks
such as diarisation, acoustic event detection or intent recognition.
The LivePerson Centre for Speech and Language Technology was established in 2017 with
the aim of conducting research into novel methods for speech recognition and general speech
processing, including end to end modelling, direct waveform modelling and new approaches
to modelling of acoustics and language. It has recently extended its research remit to spoken
and written dialogue. The Centre hosts several Research Associates, PhD researchers,
graduate and undergraduate project students, Researchers and Engineers from LivePerson,
and academic visitors, which will provide avibrant work environmentwithin the University.
Being fully connected with SpandH brings collaboration, and access to a wide range of
academic research and opportunities for collaboration inside and outside of the University.
Thepostholder wil lwork closely with Prof.Thomas Hain who is the Director of the
LivePerson Centre and also Head of the SpandH group. Prof. Hain also leads the UKRI
Centre for Doctora lTraining InSpeech and LanguageTechnologies and their
Applications(slt-cdt.ac.uk) - a collaboration between the Natural Language Processing
(NLP) research group and SpandH. Jointly, NLP and SpandH host more than 110 active
researchers in these fields.

We’re one of the best not-for-profit organisations to work for in the UK. The University’s Total
Reward Package includes a competitive salary, a generous Pension Scheme and annual
leave entitlement, as well as access to a range of learning and development courses to
support your personal and professional development.
We build teams of people from different heritages and lifestyles from across the world, whose
talent and contributions complement each other to the greatest effect. We believe diversity in
all its forms delivers greater impact through research, teaching and student experience.
To find out what makes the University of Sheffield a remarkable place to work, watch this short
film: www.youtube.com/watch?v=7LblLk18zmo, and follow @sheffielduni and @ShefUniJobs
on Twitter for more information.

Top

Title of Project: PhD Position in Adaptive Deep Learning for Speech and Language

Supervisor:Professor Thomas Hain
Deadline for
Applications:13th April 2023
The LivePerson Centre for Speech and Language offers a 3 year fully funded PhD studentship
covering standard maintenance, fees and travel support, to work on deep neural network adaptive
learning modules for speech and language. The Centre is connected with the Speech and Hearing
(SpandH) and the Natural Language Processing(NLP) researchg roups at the Department  of
Computer Science at the University of Sheffield.
Domain mismatch remains a key issue for speech and language technologies for which traditional
solutions are transfer learning and adaptation. The latter was widely used for modelling of speech in
the context of generative models, however less so with modern neural network approaches. Such
adaptation targeted features or models and was often informed by previous model output and
estimates of latent factors. These approaches were often informed by observations on human abilities
to adapt and adjust to new acoustic or semantic situations. Adaptation in neural networks is model
based and often implicit - through attention or dynamic convolution. However, these methods to date
still fail to reproduce the rapid learning and adaptation that humans exhibit when being exposed to new
contexts.
The objective in this project is to conduct research into neural network structures that are capable of
rapidly adjusting to a change in latent factors and at the same time allow for robust control. This will
require rapid feedback mechanisms on the mismatch between the observed data and the model
expectation. A range of strategies may be applied - through instantaneous feedback or through control
of transformational model parameters. All proposals are to be implemented and tested on speech, and
where suitable, also language data. Experiments should be conducted on a range of tasks of different
complexity in the context of different data types.
The student will join a world-leading team of researchers in speech and language technology. The
LivePerson Centre for Speech and Language Technology was established in 2017 with the aim to
conduct research into novel methods for speech recognition and general speech processing, including
end-to-end modelling, direct waveform modelling and new approaches to modelling of acoustics and
language. It has recently extended its research remit to spoken and written dialogue. The Centre hosts
severalResearchAssociates,PhDresearchers,graduateandundergraduateprojectstudents,
ResearchersandEngineers from LivePerson, and academic visitors. Being fully connected with
SpandH brings collaboration, and access to a wide range of academic research and opportunities for
collaboration inside and outside of the University. The Centre has access to extensive dedicated
computing resources (GPU, large storage) and local storage of over 60TB of raw speech data

The successful applicant will work under the supervision of Prof. Hain who is the Director of the
LivePerson Centre and also Head of the SpandH research group. SpandH was and is involved in a
large number of national and international projects funded by national bodies and EU sources as well
as industry. Prof. Hain also leads the UKRI Centre for Doctoral Training In Speech and Language
Technologies and their Applications (https://slt-cdt.ac.uk/) - a collaboration between the NLP research
group and SpandH. Jointly, NLP and SpandH host more than 110 active researchers in these fields.
This project will start as soon as possible.
If English is not your first language, you must have an IELTS score of 6.5 overall, with no less than 6.0
in each component.
How to Apply:All applications must be made directly to the University of Sheffield using the
Postgraduate Online Application Form.
Information on what documents are required and a link to the application form can
be found here - https://www.sheffield.ac.uk/postgraduate/phd/apply/applying
On your application, please name Prof. Thomas Hain as your proposed supervisor
and include the title of the studentship you wish to apply for.
Your research proposal should:
●Be no longer than 4 A4 pages, including references
●Outline your reasons for applying for this studentship
●Explain how you would approach the research, including details of your
skills and experience in the topic area
If you have any queries, please contact phd-compsci@sheffield.ac.uk
Funding
Details:
This position is fully funded by LivePerson, covering all tuition fees and a stipend at
the standard UKRI rate.

Top

Deux postes de MCF en phonétique sont ouverts au concours à l'Université Paul-Valéry Montpellier 3 cette année :

Phonétique générale et traitement outillé de l'oral (UMR 5267 Praxiling) : https://www.galaxie.enseignementsup-recherche.gouv.fr/ensup/ListesPostesPublies/ANTEE/2023_1/0341089Z/FOPC_0341089Z_4352.pdf

Phonétique et Didactique de l'oral en FLE (acquisition / appropriation des langues) : https://www.galaxie.enseignementsup-recherche.gouv.fr/ensup/ListesPostesPublies/ANTEE/2023_1/0341089Z/FOPC_0341089Z_4353.pdf

Date limite : 30 mars 2023

Top

Stockholm

Ref. No. SU FV-0793-23

Closing date: 15/04/2023

URL to this page
https://www.su.se/english/about-the-university/work-at-su/available-jobs/phd-student-positions-1.507588?rmpage=job&rmjob=20262&rmlang=UK

Top

The Department of Linguistics at Stockholm University invites applications for a PhD student position in experimental phonetics, including (but not limited to) topics in prosody. For details, see: https://www.su.se/english/about-the-university/work-at-su/available-jobs/phd-student-positions-1.507588?rmpage=job&rmjob=20262&rmlang=UK .

Top

The Digital Linguistics Lab at Bielefeld University (head: JProf. Dr.-Ing. Hendrik Buschmeier) is seeking to fill a research position (PhD-student, E13 TV-L, 100%, fixed-term) in the area of multimodal human-robot interaction in the research project ?Hybrid Living?.

Join us to work in an interdisciplinary team on research questions in the intersection of human-robot interaction and computational linguistics. Specifically, you will work (1) on the use of multimodal communication (verbal and nonverbal) to situatively instruct a service robot, (2) on making the robot's behaviour transparent to its users, and (3) on models for solving human-robot interaction problems through communication.

The formal job advertisement, with information on how to apply, can be found here: https://uni-bielefeld.hr4you.org/job/view/2265/research-position-in-multimodal-human-robot-interaction?page_lang=en

Questions? Don't hesitate to get in touch: hbuschme@uni-bielefeld.de

Hendrik Buschmeier

Top

We are seeking a multimodal designer to take on a central role in the Shared Reality Lab?s open source IMAGE project (image.a11y.mcgill.ca), focused on making photos, charts, and maps available to people who are blind or low vision. We are currently operating under two grants, focused on integrating haptic force feedback and pin array devices into IMAGE. You will work with a multidisciplinary team of user experience researchers, designers, and developers who will support you in designing and releasing multimodal audio and haptic experiences that will delight our end users. The primary requirement is a strong background and passion for owning both design and iterative testing of combined audio/haptic end-user experiences. Since the goal of IMAGE is to release a practical solution that can be used on a daily basis, the candidate will work directly with developers and the rest of the team to make sure that ideas and designs get translated into implementable requirements, then deployed into production.

Requirements:

• Demonstrated experience designing and creating multimodal experiences, including audio and haptics. Please include portfolio, or links to projects.
• Ability to work with user experience researchers to clearly define user needs and specific implementation requirements to meet them.
• Comfortable working directly with developers to make sure the experiences are implementable within the project timeline and available resources.
• Prototyping experience.
• Designing and carrying out methodologically sound user testing in consultation with our existing user studies lead.
• Strong plus: Sensitization to development issues, software release cycles, software architecture, client-server tradeoffs, audio synthesis.
• Bonus: French, spoken and/or written.
• Bonus: Experience working with the blind/low vision community.

Other useful skills (not required). If the candidate has the desire and capability, they are also welcome to participate in software architecture and implementation, for example:

• Audio synthesis experience. (IMAGE currently uses SuperCollider)
• Software architecture, design, and documentation, including creating usable solutions for developers and content creators in a client/server model.
• Mentoring junior designers/developers.

Candidates applying as a research assistant must be eligible to work in Canada.

Those applying as postdoctoral candidates should refer to McGill?s requirements on postdoctoral appointments, www.mcgill.ca/gps/postdocs, for conditions and additional information on the status of the position. (In Quebec, a Postdoctoral Fellow is a full-time student status and trainee category, and the Ministère de l'Education, Enseignement Supérieur et Recherche (MESRS) stipulates that all postdocs must be registered on a university student registration system.) Please note that non-Canadian postdoctoral fellows must obtain valid Citizenship or an Immigration Canada (CIC) work permit to legally work in Canada.

To apply for the position, please email the following items to Jeremy Cooperstock (srl-jobs@cim.mcgill.ca):

• A brief letter of application, describing your qualifications and relevant experience to the position of interest, along with your dates of availability.
• Detailed CV with links to online papers and/or project portfolios.
• Two (2) reference letters (sent separately).

The position is available immediately, with an initial appointment of up to one year. Informal inquiries are welcome.

About us: The Shared Reality Lab conducts research in audio, video, and haptic technologies, building systems that leverage their capabilities to facilitate and enrich both human-computer and computer-mediated human-human interaction. The lab is part of the Centre for Intelligent Machines and Department of Electrical and Computer Engineering of McGill University. McGill, one of Canada's most prestigious universities, is located in Montreal, a top city to live in, especially for students.
 
McGill University is committed to equity in employment and diversity. It welcomes applications from Aboriginal persons, persons with disabilities, ethnic minorities, persons of minority sexual orientation or gender identity, visible minorities, women and others who may contribute to diversification. All qualified applicants are encouraged to apply, although Canadians and permanent residents will be given priority.

Top

We have an open 4yr PhD position in the SPEAC labhttps://hrbosker.github.io (Speech Perception in Audiovisual Communication) at the Donders Institute, Radboud University, Nijmegen, The Netherlands.

The position is funded through an ERC Starting Grant (HearingHands, 101040276) awarded to Dr. Hans Rutger Bosker. We are looking for candidates with a strong background in speech perception and an interest in audiovisual prosody and gesture-speech integration.

You will work closely with Dr. Hans Rutger Bosker (PI) and Prof. James McQueen (promotor). The PhD project aims to determine how and when the timing of seemingly meaningless up-and-down hand gestures influences audiovisual speech perception, specifically targeting more naturalistic communicative settings. You will use virtual avatars, allowing careful control of their gestural movements, to establish which kinematic and communicative properties of hand gestures influence low-level speech perception. You will assess how challenging listening conditions impact the perceptual weighting of visual, auditory and audiovisual cues to prominence, as well as determine the time-course of these cues using eye-tracking. Finally, you will design training studies to test how humans adjust their perception to between-talker variation in gesture-speech alignment.

- 4 year contract, 1.0 FTE

- gross monthly salary: ? 2,541 - ? 3,247 (scale P)

- application deadline: May 22, 2023

- preferred starting date: September 1, 2023

More details about the project, profile, and what we have to offer is available through the link below. If you have any questions, do get in touch at HansRutger.Bosker@donders.ru.nl

https://www.ru.nl/en/working-at/job-opportunities/phd-candidate-audiovisual-speech-perception-at-the-donders-centre-for-cognition

Top

University of Washington, Seattle, WA, USA

Laboratory for Speech Physiology and Motor Control 

Post-doctoral position in speech sensorimotor learning in typical adults,

DBS patients, and adults who stutter

The Laboratory for Speech Physiology and Motor Control (PI Ludo Max, Ph.D.) at the University of Washington (Seattle) is seeking to fill a post-doctoral position in the areas of sensorimotor integration and sensorimotor learning for speech production. The position will involve experimental work on sensorimotor adaptation, sensory prediction, and error evaluation in typical adults, Parkinson’s and essential tremor patients with deep brain stimulation implants (DBS), and adults who stutter. The lab is located in the University of Washington's Department of Speech and Hearing Sciences and has additional affiliations with the Graduate Program in Neuroscience, the Department of Bioengineering, and the Department of Linguistics.

The successful candidate will use speech sensorimotor adaptation paradigms (with digital signal processing perturbations applied to the real-time auditory feedback or mechanical loads applied to the jaw by a robotic device) to investigate various aspects of motor learning and control. Data collection will involve acoustic, kinematic, and neural data to investigate auditory-motor interactions during speech movement planning and execution.

The appointment is initially for one year, with renewal possible contingent upon satisfactory performance and productivity. We are looking for a candidate available to start in the summer of 2023, and applicants should have completed all requirements for their Ph.D. degree by that time. Review of applications will begin immediately. Candidates with a Ph.D. degree in neuroscience, cognitive/behavioral neuroscience, motor control/kinesiology, biomedical engineering, communication disorders/speech science, and related fields, are encouraged to apply.

For more information, please contact lab director Ludo Max, Ph.D. (LudoMax@uw.edu). Applications can be submitted to the same e-mail address. Interested candidates should submit (a) a cover letter describing their research experiences, interests, and goals, (b) a curriculum vitae, (c) the names and contact information of three individuals who can serve as references, and (d) reprints of relevant journal publications.

Top

Dans le cadre d'un projet PIA, nous avons trois offres de post-doc d'une durée de 2 ans,
ouvertes sur le site toulousain : reconnaissance automatique de la parole, analyse de
sentiments et modélisation de préférences, pour un assistant vocal embarqué dans les
véhicules.

Plus d'info ici : https://www.irit.fr/~Thomas.Pellegrini/pdf/postdoc_3offers_2023.pdf

Top

Offre d’emploi : 1 Chargé.e de recherche et développement (H/F) Conversion neuronale de l’identité vocale pour la réalisation d’attaques adverses

Disponibilité et durée : 18 mois, de préférence à partir du 01 juin 2023

Description du poste: Dans le cadre du projet ANR BRUEL (2022-2026), l’équipe Analyse et Synthèse des sons recherche un.e chargé.e de recherche pour la conception, l’implémentation, et l’apprentissage d’algorithmes de conversion neuronale de l’identité vocale pour la création d’attaques d’usurpation d’identité. A partir d’un ensemble de scénarios d’attaques envisagées pour réaliser ces attaques en fonction des moyens et ressources disponibles (expertise, algorithmes, données), les travaux consisteront dans un premier temps à réaliser l’implémentation d’un banc d’essais d’algorithmes pour évaluer la robustesse des systèmes d’authentification et de détection face à ces attaques. Les travaux porteront dans un second temps sur l’une ou plusieurs des problématiques suivantes : - L’apprentissage de la conversion d’identité à partir de données de qualité hétérogène et dégradée (compression, bruits, etc…) librement accessibles (par exemple sur internet), et le transfert d’identité à partir de peu de données par des stratégies d’adaptation neuronale à partir de peu d’exemples; - La génération de conversions avec un contrôle de l’emprunte acoustique pour que l’attaque soit adaptée à l’environnement sonore et au canal de communication en fonction des scénarios envisagés (depuis des conditions professionnelles jusqu’à des conditions dégradées de communication téléphonique ou internet). L’ensemble des travaux réalisés seront évalués selon les protocoles usuels en conversion d’identité vocale, mais également en relation avec les partenaires du projet pour mesurer les performances des systèmes d’authentification/détection en fonction des scénarios envisagés. Les avancées réalisées seront intégrées au système de conversion neuronale de l'identité vocale de l’Ircam et évaluées in situ dans le cadre de productions professionnelles et/ou artistiques réalisées à l’Ircam. Le.a chargé.e de recherche collaborera également avec l’équipe de développement et participera aux activités du projet (évaluation des algorithmes, réunions, spécifications, livrables, rapports).

Présentation du projet BRUEL Le projet ANR BRUEL (ElaBoRation d’Une méthodologie d’EvaLuation des systèmes d’identification par la voix) concerne l’évaluation/certification des systèmes d’identification par la voix face aux attaques adverses. En effet, les systèmes de reconnaissance automatique du locuteur sont vulnérables non seulement à la parole produite artificiellement par synthèse vocale, mais aussi à d'autres formes d'attaques telles que la conversion d’identité vocale et la relecture. Les artefacts créés lors de la création ou la manipulation de ces attaques frauduleuses constituent les marques laissées dans le signal par les algorithmes de synthèse vocale permettant ainsi de distinguer la voix réelle originale d’une voix usurpée. Dans ces conditions, la détection de l'usurpation d'identité requiert d'évaluer les contre-mesures d'usurpation d'identité en même temps que les systèmes de reconnaissance du locuteur. Le projet BRUEL ambitionne de proposer la première méthodologie d’évaluation/certification des systèmes d'identification par la voix basée sur une approche Critères Communs.

Contexte de travail Le travail sera effectué à l’IRCAM au sein de l’équipe Analyse et Synthèse des sons encadré par Nicolas Obin et Axel ROEBEL (SU, CNRS, IRCAM). Le travail pourra être mené partiellement à distance, avec la nécessité d’une participation aux réunions d’avancement du projet. L'Ircam est une association à but non lucratif, associée au Centre National d'Art et de Culture Georges Pompidou, dont les missions comprennent des activités de recherche, de création et de pédagogie autour de la musique du XXème siècle et de ses relations avec les sciences et technologies. Au sein de l'unité mixte de recherche, UMR 9912 STMS (Sciences et Technologies de la Musique et du Son) commune à l’Ircam, à Sorbonne Université, au CNRS, et au Ministère de la Culture et de la Communication, des équipes spécialisées mènent des travaux de recherche et de développement informatique dans les domaines de l'acoustique, du traitement des signaux sonores, des sciences cognitives, des technologies d’interaction, de l’informatique musicale et de la musicologie.

L'Ircam est situé au centre de Paris à proximité du Centre Georges Pompidou au 1, Place Stravinsky 75004 Paris.

Expérience et compétences requises: Nous recherchons un.e candidat.e spécialisé.e en apprentissage de réseaux de neurones profonds et en traitement automatique de la parole ou en vision, de préférence en deep fakes. Le·a candidate devra avoir une thèse de doctorat en sciences informatiques dans les domaines de l’apprentissage par réseaux de neurones profonds, ainsi que des publications dans des conférences et revues reconnues dans le domaine. Le·a candidat·e idéal·e aura:

• Une solide expertise en apprentissage machine, et en particulier en réseaux de neurones profonds.

• Une bonne expérience en traitement automatique de la parole ; de préférence dans le domaine de la génération ou des deep-fakes;

• Maîtrise du traitement du signal audio-vidéo numérique;

• Une excellente maîtrise du langage de programmation Python, de l’environnement TensorFlow pour l’apprentissage de réseaux de neurones, et du calcul distribué sur des serveurs GPUs

• Excellente maîtrise de l’anglais scientifique parlé et écrit

• Autonomie, travail en équipe, productivité, rigueur et méthodologie

Salaire Selon formation et expérience professionnelle

Candidatures Prière d'envoyer une lettre de motivation et un CV détaillant le niveau d'expérience/expertise dans les domaines mentionnés ci-dessus (ainsi que tout autre information pertinente) à Nicolas.Obin@ircam.fr et Axel.Roebel@ircam.fr Date limite de candidature 31 mai 2023

Top

Offre d’emploi : 1 Chargé.e de recherche et développement (H/F) Génération de deep fakes audio-visuel

Disponibilité et durée : 15 mois, de préférence à partir du 01 juin 2023

Description du poste Dans le cadre du projet ASTRID DeTOX (2023-2025), l’équipe Analyse et Synthèse des sons recherche un.e chargé.e de recherche pourl’implémentation et l’apprentissage d’algorithmes pour la génération de deep fakes audio-visuels avec les missions suivantes : - Collection, implémentation, et apprentissage d’algorithmes représentatifs de l’état-del’art pour la génération de deep fakes audio et visuel - Implémentation d’un nouvel algorithme de génération de deep fakes audio-visuel avec synchronisation des deux modalités en particulier pour assurer la cohérence de la parole et du mouvement du lèvre et du bas du visage - Construction de bases de données audio-visuel des personnes ciblées et apprentissage de modèles de génération de deep fakes pour ces personnes Le.a chargé.e de recherche collaborera également avec l’équipe de développement et participera aux activités du projet (évaluation des algorithmes, réunions, spécifications, livrables, rapports). Présentation du projet DeTOX Les récents challenges ont montré qu'il était extrêmement difficile de mettre au point des détecteurs universels de vidéos hyper-truquées - à l'exemple des 'deep fakes' utilisés pour contrefaire l'identité d'une personne. Lorsque les détecteurs sont exposés à des vidéos générées par un algorithme nouveau, c'est-à-dire inconnu lors de la phase d'apprentissage, les performances sont encore extrêmement limitées. Pour la partie vidéo, les algorithmes examinent les images une par une, sans tenir compte de l'évolution de la dynamique faciale au cours du temps. Pour la partie vocale, la voix est générée de manière indépendante de la vidéo ; en particulier, la synchronisation audio-vidéo entre la voix et les mouvements des lèvres n'est pas prise en compte. Ceci constitue un point faible important des algorithmes de génération de vidéos hyper-truquées. Le présent projet vise à implémenter et à apprendre des algorithmes de détection de deepfakes personnalisés sur des individus pour lesquels on peut disposer et/ou fabriquer de nombreuses séquences audio-vidéo réelles et falsifiées. En se basant sur des briques technologiques de base en audio et vidéo récupérées de l'état de l'art, le projet se concentrera sur la prise en compte de l'évolution temporelle des signaux audio-visuels et de leur cohérence pour la génération et la détection. Nous souhaitons ainsi démontrer qu'en utilisant simultanément l’audio et la vidéo et en se focalisant sur une personne précise lors de l'apprentissage et de la détection, il est possible de concevoir des détecteurs efficaces même face à des générateurs encore non répertoriés. De tels outils permettront de scruter et de détecter sur le web d'éventuelles vidéos hyper-truquées de personnalités françaises importantes (président de la république, journalistes, chef d'étatmajor des armées, ...) et ce dès leur publication.

Contexte de travail Le travail sera effectué à l’IRCAM au sein de l’équipe Analyse et Synthèse des sons encadré par Nicolas Obin et Axel ROEBEL (SU, CNRS, IRCAM). Le travail pourra être mené partiellement à distance, avec la nécessité d’une participation aux réunions d’avancement du projet. L'Ircam est une association à but non lucratif, associée au Centre National d'Art et de Culture Georges Pompidou, dont les missions comprennent des activités de recherche, de création et de pédagogie autour de la musique du XXème siècle et de ses relations avec les sciences et technologies. Au sein de l'unité mixte de recherche, UMR 9912 STMS (Sciences et Technologies de la Musique et du Son) commune à l’Ircam, à Sorbonne Université, au CNRS, et au Ministère de la Culture et de la Communication, des équipes spécialisées mènent des travaux de recherche et de développement informatique dans les domaines de l'acoustique, du traitement des signaux sonores, des sciences cognitives, des technologies d’interaction, de l’informatique musicale et de la musicologie.

L'Ircam est situé au centre de Paris à proximité du Centre Georges Pompidou au 1, Place Stravinsky 75004 Paris.

Expérience et compétences requises Nous recherchons un.e candidat.e spécialisé.e en apprentissage de réseaux de neurones profonds et en traitement automatique de la parole ou en vision, de préférence en deep fakes. Le·a candidate devra avoir une thèse de doctorat en sciences informatiques dans les domaines de l’apprentissage par réseaux de neurones profonds, ainsi que des publications dans des conférences et revues reconnues dans le domaine. Le·a candidat·e idéal·e aura:

• Une solide expertise en apprentissage machine, et en particulier en réseaux de neurones profonds.

• Une bonne expérience en traitement automatique de la parole ou en vision ; de préférence dans le domaine des deep-fakes;

• Maîtrise du traitement du signal audio-vidéo numérique;

• Une excellente maîtrise du langage de programmation Python, de l’environnement TensorFlow pour l’apprentissage de réseaux de neurones, et du calcul distribué sur des serveurs GPUs

• Excellente maîtrise de l’anglais scientifique parlé et écrit

• Autonomie, travail en équipe, productivité, rigueur et méthodologie

Salaire Selon formation et expérience professionnelle

Candidatures Prière d'envoyer une lettre de motivation et un CV détaillant le niveau d'expérience/expertise dans les domaines mentionnés ci-dessus (ainsi que tout autre information pertinente) à Nicolas.Obin@ircam.fr et Axel.Roebel@ircam.fr Date limite de candidature 31 mai 2023

Top