ISCA - International Speech
Communication Association

ISCApad Archive  »  2022  »  ISCApad #292  »  Jobs  »  (2022-08-22) PhD in ML/NLP – Efficient, Fair, robust and knowledge informed self-supervised learning for speech processi

ISCApad #292

Wednesday, October 05, 2022 by Chris Wellekens

6-26 (2022-08-22) PhD in ML/NLP – Efficient, Fair, robust and knowledge informed self-supervised learning for speech processi

PhD in ML/NLP – Efficient, Fair, robust and knowledge informed self-supervised learning for speech processing

Starting date: November 1st, 2022 (flexible)

Application deadline: September 5th, 2022

Interviews (tentative): September 19th, 2022

Salary: ~2000€ gross/month (social security included)

Mission: research oriented (teaching possible but not mandatory)


Keywords: speech processing, natural language processing, self-supervised learning, knowledge informed learning, Robustness, fairness



The ANR project E-SSL (Efficient Self-Supervised Learning for Inclusive and Innovative Speech Technologies) will start on November 1st 2022. Self-supervised learning (SSL) has recently emerged as one of the most promising artificial intelligence (AI) methods as it becomes now feasible to take advantage of the colossal amounts of existing unlabeled data to significantly improve the performances of various speech processing tasks.



Recent SSL models for speech such as HuBERT or wav2vec 2.0 have shown an impressive impact on downstream tasks performance. This is mainly due to their ability to benefit from a large amount of data at the cost of a tremendous carbon footprint rather than improving the efficiency of the learning. Another question related to SSL models is their unpredictable results once applied to realistic scenarios which exhibit their lack of robustness. Furthermore, as for any pre-trained models applied in society, it is important to be able to measure the bias of such models since they can augment social unfairness.


The goals of this PhD position are threefold:

- to design new evaluation metrics for SSL of speech models ;

- to develop knowledge-driven SSL algorithms ;

- to propose methods for learning robust and unbiased representations 


SSL models are evaluated with downstream task-dependent metrics e.g., word error rate for speech recognition. This couple the evaluation of the universality of SSL representations to a potentially biased and costly fine-tuning that also hides the efficiency information related to the pre-training cost. In practice, we will seek to measure the training efficiency as the ratio between the amount of data, computation and memory needed to observe a certain gain in terms of performance on a metric of interest i.e., downstream dependent or not. The first step will be to document standard markers that can be used as robust measurements to assess these values robustly at training time. Potential candidates are, for instance, floating point operations for computational intensity, number of neural parameters coupled with precision for storage, online measurement of memory consumption for training and cumulative input sequence length for data.


Most state-of-the-art SSL models for speech rely on masked prediction e.g. HuBERT and WavLM, or contrastive losses e.g. wav2vec 2.0. Such prevalence in the literature is mostly  linked to the size, amount of data and computational resources injected by the company producing these models. In fact, vanilla masking approaches and contrastive losses may be identified as uninformed solutions as they do not benefit from in-domain expertise. For instance, it has been demonstrated that blindly masking frames in the input signal i.e. HuBERT and WavLM results in much worse downstream performance than applying unsupervised phonetic boundaries [Yue2021] to generate informed masks. Recently some studies have demonstrated the superiority of an informed multitask learning strategy carefully selecting self-supervised pretext-tasks with respect to a set of downstream tasks, over the vanilla wav2vec 2.0 contrastive learning loss [Zaiem2022]. In this PhD project, our objective is: 1. continue to develop knowledge-driven SSL algorithms reaching higher efficiency ratios and results at the convergence, data consumption and downstream performance levels; and 2. scale these novel approaches to a point enabling the comparison with current state-of-the-art systems and therefore motivating a paradigm change in SSL for the wider speech community.


Despite remarkable performance on academic benchmarks, SSL powered technologies e.g. speech and speaker recognition, speech synthesis and many others may exhibit highly unpredictable results once applied to realistic scenarios. This can translate into a global accuracy drop due to a lack of robustness to adversarial acoustic conditions, or biased and discriminatory behaviors with respect to different pools of end users. Documenting and facilitating the control of such aspects prior to the deployment of SSL models into the real-life is necessary for the industrial market. To evaluate such aspects, within the project, we will create novel robustness regularization and debasing techniques along two axes: 1. debasing and regularizing speech representations at the SSL level; 2. debasing and regularizing downstream-adapted models (e.g. using a pre-trained model).


To ensure the creation of fair and robust SSL pre-trained models, we propose to act both at the optimization and data levels following some of our previous work on adversarial protected attribute disentanglement and the NLP literature on data sampling and augmentation [Noé2021]. Here, we wish to extend this technique to more complex SSL architectures and more realistic conditions by increasing the disentanglement complexity i.e. the sex attribute studied in [Noé2021] is particularly discriminatory. Then, and to benefit from the expert knowledge induced by the scope of the task of interest, we will build on a recent introduction of task-dependent counterfactual equal odds criteria [Sari2021] to minimize the downstream performance gap observed in between different individuals of certain protected attributes and to maximize the overall accuracy. Following this multi-objective optimization scheme, we will then inject further identified constraints as inspired by previous NLP work [Zhao2017]. Intuitively, constraints are injected so the predictions are calibrated towards a desired distribution i.e. unbiased.



  • Master 2 in Natural Language Processing, Speech Processing, computer science or data science.

  • Good mastering of  Python programming and  deep learning framework.

  • Previous in Self-Supervised Learning, acoustic modeling or ASR would be a plus

  • Very good communication skills in English

  • Good command of French would be a plus but is not mandatory 




The thesis will be conducted within the Getalp teams of the LIG laboratory ( and the LIA laboratory ( The GETALP team and the LIA have a strong expertise and track record in Natural Language Processing and speech processing. The recruited person will be welcomed within the teams which offer a stimulating, multinational and pleasant working environment.

The means to carry out the PhD will be provided both in terms of missions in France and abroad and in terms of equipment. The candidate will have access to the cluster of GPUs of both the LIG and LIA. Furthermore, access to the National supercomputer Jean-Zay will enable to run large scale experiments.

The PhD position will be co-supervised by Mickael Rouvier (LIA, Avignon) and Benjamin Lecouteux and François Portet (Université Grenoble Alpes). Joint meetings are planned on a regular basis and the student is expected to spend time in both places. Moreover, the PhD student will collaborate with several team members involved in the project in particular the two other PhD candidates who will be recruited  and the partners from LIA, LIG and Dauphine Université PSL, Paris. Furthermore, the project will involve one of the founders of SpeechBrain, Titouan Parcollet with whom the candidate will interact closely.




Applications must contain: CV + letter/message of motivation + master notes + be ready to provide letter(s) of recommendation; and be addressed to Mickael Rouvier (, Benjamin Lecouteux ( and François Portet ( We celebrate diversity and are committed to creating an inclusive environment for all employees.



[Noé2021] Noé, P.- G., Mohammadamini, M., Matrouf, D., Parcollet, T., Nautsch, A. & Bonastre, J.- F. Adversarial Disentanglement of Speaker Representation for Attribute-Driven Privacy Preservation in Proc. Interspeech 2021 (2021), 1902–1906.

[Sari2021] Sarı, L., Hasegawa-Johnson, M. & Yoo, C. D. Counterfactually Fair Automatic Speech Recognition. IEEE/ACM Transactions on Audio, Speech, and Language Processing 29, 3515–3525 (2021)

[Yue2021] Yue, X. & Li, H. Phonetically Motivated Self-Supervised Speech Representation Learning in Proc. Interspeech 2021 (2021), 746–750.

[Zaiem2022]  Zaiem, S., Parcollet, T. & Essid, S. Pretext Tasks Selection for Multitask Self-Supervised Speech Representation in AAAI, The 2nd Workshop on Self-supervised Learning for Audio and Speech Processing, 2023 (2022).

[Zhao2017] Zhao, J., Wang, T., Yatskar, M., Ordonez, V. & Chang, K. - W. Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints in Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (2017), 2979–2989.

Back  Top

 Organisation  Events   Membership   Help 
 > Board  > Interspeech  > Join - renew  > Sitemap
 > Legal documents  > Workshops  > Membership directory  > Contact
 > Logos      > FAQ
       > Privacy policy

© Copyright 2024 - ISCA International Speech Communication Association - All right reserved.

Powered by ISCA