ISCA - International Speech
Communication Association


ISCApad Archive  »  2021  »  ISCApad #271  »  Journals

ISCApad #271

Monday, January 11, 2021 by Chris Wellekens

7 Journals
7-1CfP IEEE JSTSP Special Issue on Tensor Decomposition for Signal Processing and Machine Learning

Call for Papers
IEEE JSTSP Special Issue on

Tensor Decomposition for Signal Processing
and Machine Learning

 Extended deadline:August 1, 2020

Tensor decomposition, also called tensor factorization, is very useful for representing and analyzing multidimensional data. Tensor decomposition has been applied in signal processing (speech, audio, communications, radar, biomedicine), machine learning (clustering, dimensionality reduction, latent factor models, subspace learning), and beyond. Tensor decomposition helps us to learn a variety of models, including community models, probabilistic context-free-grammars, the Gaussian mixture model, and two-layer neural networks.
 
The multidimensional nature of the signals and even ?bigger? data provide a good opportunity to exploit tensor-based models and tensor network, with the aim of meeting the strong requirements on flexibility, convergence, and efficiency. Although considerable research has been done on this subject, there are many challenges still outstanding that need to be explored, like high computational cost of algorithms, tensor deflation, massive tensor decomposition, etc. The goal of this special issue is to attract high quality papers containing original research on tensor methods, tensor decompositions for signal processing and machine learning, and their applications in big data, social network, biomedical and healthcare, advanced data-driven information and communication technology (ICT) systems and others.

Potential topics include but are not limited to:

  • New tensor decompositions and uniqueness issues of tensor models
  • Low-rank approximations
  • Fast and robust tensor decompositions
  • Novel algorithms for existing tensor decomposition models
  • Optimization problems related to tensor models
  • Tensor-based detection and parameter estimation
  • Tensor decomposition for 5G/B5G wireless communications
  • Tensor-based data-driven networking
  • Tensor processing and analysis in social networks
  • Tensor decomposition for industry internet of things
  • Spatial temporal data via tensor factorization
  • Computer vision with tensor method
  • Biomedical, healthcare, and audio signal processing with tensors
  • Pattern recognition and neural networks with tensor decomposition

Submission Guidelines


Prospective authors should follow the instructions given on the IEEE JSTSP webpages and submit their manuscript to the web submission system.

Important Dates

  • Manuscript submissions due: August 1, 2020 extended
  • First review due: September 1, 2020
  • Revised manuscript due: November 1, 2020
  • Second review due: December 15, 2020
  • Final manuscript due: January 15, 2021

Guest Editors


 

 
Back  Top

7-2Special issue on Voice Privacy, Computer, Speech and Language
COMPUTER SPEECH AND LANGUAGE
 
Special issue on Voice Privacy  
 
Deadline: January 31, 2021
 
Recent years have seen mounting calls for the preservation of privacy when treating personal data. Speech falls within that scope because it encapsulates a wealth of personal information that can be revealed by listening or by automatic speech analysis and recognition systems. This includes, e.g., age, gender, ethnic origin, geographical background, health or emotional state, political orientations, and religious beliefs, among others. In addition, speaker recognition systems can reveal the speaker?s identity. It is thus of no surprise that efforts to develop privacy preservation solutions for speech technology are starting to emerge.
 
A few studies have tackled the formal definition of privacy preservation, the provision of suitable datasets, and the design of evaluation protocols and metrics based on user and attacker models. Other studies have addressed the development of privacy preservation methods which maximize the utility for users while defeating attackers. Current methods fall into four categories: deletion, encryption, anonymization, and distributed learning. Deletion methods aim to delete or obfuscate speech based on speech enhancement or privacy-preserving feature extraction for ambient sound analysis purposes. Encryption methods such as fully homomorphic encryption and secure multiparty computation can be used to implement all computations in the encrypted domain. Anonymization methods aim to suppress personal information but retain other information by means of noise addition, speech transformation, voice conversion, speech synthesis, or adversarial learning. Decentralized or federated learning methods aim to learn models (for, e.g., keyword spotting) from distributed data without accessing individual data points nor leaking information about them in the models.
 

This special issue solicits papers describing advances in privacy protection for speech processing systems, including theoretical developments, algorithms or systems.

Examples of topics relevant to the special issue include (but are not limited to):
  • formal models of speech privacy preservation,
  • privacy-preserving speech feature extraction,
  • privacy-driven speech deletion or obfuscation,
  • privacy-driven voice conversion,
  • privacy-driven speech synthesis and transformation,
  • privacy-preserving decentralized learning of speech models,
  • speech processing in the encrypted domain,
  • open resources, e.g., datasets, software or hardware implementations, evaluation recipes, objective and subjective metrics.
 
Submission instructions: 

Manuscript submissions shall be made through: https://www.editorialmanager.com/YCSLA/.

The submission system will be open early October. When submitting your manuscript please select the article type ?VSI: Voice Privacy?. Please submit your manuscript before the submission deadline.

All submissions deemed suitable to be sent for peer review will be reviewed by at least two independent reviewers. Once your manuscript is accepted, it will go into production, and will be simultaneously published in the current regular issue and pulled into the online Special Issue. Articles from this Special Issue will appear in different regular issues of the journal, though they will be clearly marked and branded as Special Issue articles.
Please see an example here: https://www.sciencedirect.com/journal/science-of-the-total-environment/special-issue/10SWS2W7VVV
Please ensure you read the Guide for Authors before writing your manuscript. The Guide for Authors and the link to submit your manuscript is available on the Journal?s homepage https://www.elsevier.com/locate/csl.

 
Important dates:

January 8, 2021: Paper submission
May 7, 2021: First review
July 9, 2021: Revised submission
September 10, 2021: Final decision
October 8, 2021: Camera-ready submission

 
Guest Editors:
Emmanuel Vincent, Inria
Natalia Tomashenko, Avignon Université
Junichi Yamagishi, National Institute of Informatics and University of Edinburgh
Nicholas Evans, EURECOM
Paris Smaragdis, University of Illinois at Urbana-Champaign
Jean-François Bonastre, Avignon Université
Back  Top

7-3Special issue of Neural Networks on Advances in Deep Learning Based Speech Processing (Updated)
NEURAL NETWORKS
 
Special issue on
Advances in Deep Learning Based Speech Processing

Extended deadline: August 30, 2020

Earlier submissions will be handled as they come. Accepted manuscripts will be published without waiting for later submissions.
 

  
Deep learning has triggered a revolution in speech processing. The revolution started from the successful application of deep neural networks to automatic speech recognition, and quickly spread to other topics of speech processing, including speech analysis, speech denoising and separation, speaker and language recognition, speech synthesis, and spoken language understanding. This tremendous success has been achieved thanks to the advances in neural network technologies as well as the explosion of speech data and fast development of computing power.

Despite this success, deep learning based speech processing still faces many challenges for real-world wide deployment. For example, when the distance between a speaker and a microphone array is larger than 10 meters, the word error rate of a speech recognizer may be as high as over 50%; end-to-end deep learning based speech processing systems have shown potential advantages over hybrid systems, however, they require large-scale labelled speech data; deep learning based speech synthesis has been highly competitive with human-sounding speech and much better than traditional methods, however, the models are not stable, lack controllability and are still too large and slow to be deployed onto mobile and IoT devices.

Therefore, new methods and algorithms in deep learning and speech processing are needed to tackle the above challenges, as well as to yield novel insights into new directions and applications.

This special issue aims to accelerate research progress by providing a forum for researchers and practitioners to present their latest contributions that advance theoretical and practical aspects of deep learning based speech processing techniques. The special issue will feature theoretical articles with novel new insights, creative solutions to key research challenges, and state-of-the-art speech processing algorithms/systems that demonstrate competitive performance with potential industrial impacts. The ideas addressing emerging problems and directions are also welcome.
 

 

Topics of interest for this special issue include, but are not limited to:
?   Speaker separation
?   Speech denoising
?   Speech recognition
?   Speaker and language recognition
?   Speech synthesis
?   Audio and speech analysis
?   Multimodal speech processing
 
 
Submission instructions: 
Prospective authors should follow the standard author instructions for Neural Networks, and submit manuscripts online at https://www.editorialmanager.com/neunet/default.aspx.
Authors should select ?VSI: Speech Based on DL' when they reach the 'Article Type' step and the 'Request Editor' step in the submission process.

 
Important dates: 
June 30, 2020 - Submission deadline
September 30, 2020 - First decision notification
November 30, 2020 - Revised version deadline
December 31, 2020 - Final decision notification
March, 2021 - Publication
 
 
Guest Editors: 

Xiao-Lei Zhang, Northwestern Polytechnical University, China
Lei Xie, Northwestern Polytechnical University, China
Eric Fosler-Lussier, Ohio State University, USA
Emmanuel Vincent, Inria, France

Back  Top

7-4Special issue on ' Machine Learning Applied to Music/Audio Signal Processing' in MDPI Electronics

 Special issue on ' Machine Learning Applied to Music/Audio Signal Processing' in MDPI Electronics at 
https://www.mdpi.com/si/51394


Dear Colleagues,

The applications of audio and music processing range from music discovery and recommendation systems over speech enhancement, audio event detection, and music transcription, to creative applications such as sound synthesis and morphing.

The last decade has seen a paradigm shift from expert-designed algorithms to data-driven approaches. Machine learning approaches, and Deep Neural Networks specifically, have been shown to outperform traditional approaches on a large variety of tasks including audio classification, source separation, enhancement, and content analysis. With data-driven approaches, however, came a set of new challenges. Two of these challenges are training data and interpretability. As supervised machine learning approaches increase in complexity, the increasing need for more annotated training data can often not be matched with available data. The lack of understanding of how data are modeled by neural networks can lead to unexpected results and open vulnerabilities for adversarial attacks.

The main aim of this Special Issue is to seek high-quality submissions that present novel data-driven methods for audio/music signal processing and analysis and address main challenges of applying machine learning to audio signals. Within the general area of audio and music information retrieval as well as audio and music processing, the topics of interest include, but are not limited to, the following:

   - unsupervised and semi-supervised systems for audio/music processing and analysis
   - machine learning methods for raw audio signal analysis and transformation
   - approaches to understanding and controlling the behavior of audio processing systems such as visualization, auralization, or regularization methods
   - generative systems for sound synthesis and transformation
   - adversarial attacks and the identification of 'deepfakes' in audio and music
   - audio and music style transfer methods
   - audio recording and music production parameter estimation
   - data collection methods, active learning, and interactive machine learning for data-driven approaches

Dr. Peter Knees
Dr. Alexander Lerch

Back  Top

7-5Computer Speech and Language Special issue on State-of-the-art Handcrafted Feature Extraction for Speech and Voice Analysis
Computer Speech and Language Special issue on State-of-the-art Handcrafted Feature Extraction for Speech and Voice Analysis
 
 

Aims and Scope

For over ten years, the scientific community has been witnessing a permanent rise in the number of modern feature-learning approaches for speech and voice analysis. Although those strategies have been placed at the forefront of current artificial intelligence research, uninterpretable models and high computational costs characterise their main drawbacks. Thus, the intention of this special issue is to attract the attention to the fact that, in many problems, handcrafted extraction may still provide prominent solutions with low computational costs and easy-to-interpret features.

Topics of Interest

The particular topics of interest are those focusing on handcrafted feature extraction approaches for speech and voice analysis. Applications include, but are not necessarily limited to:

• text-dependent, text-prompted and text-independent speaker identification and verification

• spoken word, limited-vocabulary and large-vocabulary speech recognition

• speech emotion identification

• speech characterisation

• voice activity detection

• idiom recognition

• speech pathology detection

• emerging applications, including coronavirus detection based on speech

Before submission, prospective authors should carefully read over the journal author guidelines before submitting the electronic copy of their complete manuscripts through the journal online submission system. Please choose 'VSI:SHFESVA' for the 'article type” during submission.

Important Dates

• submission deadline: July 30, 2020

• results from the first round of reviews: September 30, 2020

• revised papers due: October 15, 2020

• results from the second round of reviews: November 30, 2020

• re-revised papers due: December 30, 2020

• final decisions: January 30, 2021

Guest-editors

Prof. (Dr.) Rodrigo Capobianco Guido (guido@ieee.org), São Paulo State University (UNESP), Brazil

http://www.sjrp.unesp.br/~guido/

Prof. (Dr.) Hemant A. Patil ( hemant_patil@daiict.ac.in), Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar, Gujarat, India.

https://sites.google.com/site/hemantpatildaiict/

 
 
Back  Top

7-6CfP: IEEE/ACM TASLP Special Issue on the Eighth Dialog System Technology Challenge
=================================================================================
Call for Papers: IEEE/ACM TASLP Special Issue on the Eighth Dialog System Technology Challenge
=================================================================================
 

The Dialog System Technology Challenge (DSTC) is an ongoing series of research competitions for dialog systems. To accelerate the development of new dialog technologies, the DSTCs have provided common testbeds for various research problems. The Eighth Dialog System Technology Challenge (DSTC8) consists of the following four main tracks including two newly introduced tasks and two followup tasks of DSTC7.
 
  1. Multi-domain task-completion track addresses the end-to-end response generation problems in multi-domain task completion and cross-domain adaptation scenarios. 
  2. NOESIS II: Predicting Responses, Identifying Success, and Managing Complexity in Task-Oriented Dialogue explores a response selection task extending the first NOESIS track in DSTC7 and offers two additional subtasks for identifying task success and disentangling conversations. 
  3. Audio visual scene-aware dialog track is another follow-up track of DSTC7 which aims to generate dialog responses using multi-modal information given in an input video. 
  4. Schema-guided dialog state tracking revisits dialog state tracking problems in a practical setting associated with a large number of services/APIs required to build virtual assistants in practice.
This special issue will host work on any of the DSTC8 tasks. Papers may describe entries in the official DSTC8 challenge, or any research utilizing DSTC8 datasets irrespective of the participation in the official challenge. We also welcome papers that analyze the DSTC8 tasks or results themselves. Finally, we also invite papers on previous DSTC tasks as well as general technical papers on any dialog-related research problems.
 
You can get the author guide from the following link: https://signalprocessingsociety.org/publications-resources/information-authors
 
For any query regarding this special issue please contact seokim@dstc.community.
 
 
Important Dates
  • Manuscript submission date: August 15, 2020 
  • First Review Completed: October 15, 2020 
  • Revised Manuscript Due: November 30, 2020 
  • Second Review Completed: January 15, 2021 
  • Final Manuscript Due: February 28, 2021 
  • Expected publication date: May 2021
 
Guest Editors
  • Seokhwan Kim, Amazon Alexa AI, USA
  • Hannes Schulz, Microsoft Research Montreal, Canada 
  • Chulaka Gunasekara, IBM Research AI, USA 
  • Chiori Hori, Mitsubishi Electric Research Laboratories (MERL), USA 
  • Abhinav Rastogi, Google Research, USA 
  • Luis Fernando D'Haro, Universidad Politécnica de Madrid (UPM), Spain
Back  Top

7-7TAL Journal, Special issue on Natural Language Processing

Call for submission: http://tal-62-1.sciencesconf.org/ (page soon available)
TAL Journal: regular issue
2021 Volume 62-1
Editors : Cécile Fabre, Emmanuel Morin, Sophie Rosset and Pascale Sébillot

Deadline for submission: 12/15/2020

--

TOPICS
The TAL journal launches a call for papers for an open issue of the journal. We invite papers in any field of natural language processing, including:
- lexicon, syntax, semantics, discourse and pragmatics;
- morphology, phonology and phonetics;
- spoken and written language analysis and generation;
- logical, symbolic and statistical models of language;
- information extraction and text mining;
- multilingual processing, machine translation and translation tools;
- natural language interfaces and dialogue systems;
- multimodal interfaces with language components;
- language tools and resources;
- system evaluation;
- terminology, knowledge acquisition from texts;
- information retrieval;
- corpus linguistics;
- use of NLP tools for linguistic modeling;
- computer assisted language learning;
- applications of natural language processing.
Whatever the topic, papers must stress the natural language processing aspects.

'Position statement' or 'State of the art' papers are welcome.

LANGUAGE
Manuscripts may be submitted in English or French. Submissions in English are accepted only if one of the co-authors is a non French-speaking person.

THE JOURNAL
TAL (http://www.atala.org/revuetal - Traitement Automatique des Langues / Natural Language Processing) is an international journal published by ATALA (French Association for Natural Language Processing) since 1960 with the support of CNRS (National Centre for Scientific Research). It has moved to an electronic mode of publication.

IMPORTANT DATES
Deadline for submission: 12/15/2020
Notification to authors after first review: 03/15/2021
Notification to authors after second review: 05/31/2021
Publication: October, 2021


FORMAT SUBMISSION
Papers should strictly be between 20 and 25 pages long.
TAL performs double-blind review: it is thus necessary to anonymise the manuscript and the name of the pdf file and to avoid self references.


Style sheets are available for download on the Web site of the journal (http://www.atala.org/content/instructions-aux-auteurs-feuilles-de-style-0).

Authors who intend to submit a paper are encouraged to upload your contribution via the menu 'Paper submission' (PDF format). To do so, you will need to have an account on the sciencesconf platform. To create an account, go to the site http://www.sciencesconf.org and click on 'create account' next to the 'Connect' button at the top of the page. To submit, come back to the page (soon available) http://tal-62-1.sciencesconf.org/, connect to you account and upload your submission.
Back  Top

7-8Special issue at Frontiers in Psychology:Effective and Attractive Communication Signals in Social, Cultural, and Business Contexts

https://www.frontiersin.org/research-topics/15165/effective-and-attractive-communication-signals-in-social-cultural-and-business-contexts#overview

The call is open for about a year now and articles are published continuously.

Back  Top

7-9CfP IEEE/ACMTASLP Special Issue on Eighth Dialog System Technology Challenge

Call for Papers
IEEE/ACM TASLP Special Issue on

Eighth Dialog System Technology Challenge

 
   
   
 
   
The Dialog System Technology Challenge (DSTC) is an ongoing series of research competitions for dialog systems. To accelerate the development of new dialog technologies, the DSTCs have provided common testbeds for various research problems. The Eighth Dialog System Technology Challenge (DSTC8) consists of the following four main tracks including two newly introduced tasks and two followup tasks of DSTC7. 

Topics of interest in this special issue include (but are not limited to):
  1. Multi-domain task-completion track addresses the end-to-end response generation problems in multi-domain task completion and cross-domain adaptation scenarios.
     
  2. NOESIS II: Predicting Responses, Identifying Success, and Managing Complexity in Task-Oriented Dialogue explores a response selection task extending the first NOESIS track in DSTC7 and offers two additional subtasks for identifying task success and disentangling conversations.
     
  3. Audio visual scene-aware dialog track is another follow-up track of DSTC7 which aims to generate dialog responses using multi-modal information given in an input video.
     
  4. Schema-guided dialog state tracking revisits dialog state tracking problems in a practical setting associated with a large number of services/APIs required to build virtual assistants in practice. 
This special issue will host work on any of the DSTC8 tasks. Papers may describe entries in the official DSTC8 challenge, or any research utilizing DSTC8 datasets irrespective of the participation in the official challenge. We also welcome papers that analyze the DSTC8 tasks or results themselves. Finally, we also invite papers on previous DSTC tasks as well as general technical papers on any dialog-related research problems.
 
For any query regarding this special issue, please contact Seokhwan Kim.



 

 
 
Back  Top

7-10Call for Papers: Data, Replicability and Reproducibility in Linguistics in Revista da Abralin

 

Call for Papers: Data, Replicability and Reproducibility in Linguistics

For scientific theories based on empirical data, reproducibility and replicability are central principles, for at least two reasons. First, unless we accept that scientific theories rest on the authority of a small number of researchers, empirical studies should be reproducible, in the sense that their methods and procedures should be carefully documented and relevant data should be made available so that other researchers to conduct the same study and obtain the same results. Second, for empirical results to provide a solid basis for scientific theorisation, they should also be replicable in the sense that most attempts to reproduce the original study using similar data and methods would produce results similar to those presented in the original study.

 Although science depends on replicability and reproducibility, works aimed at replicating impact studies are quite rare due to the emphasis academia places on novelty: editors and reviewers of journals usually value original research higher than replication studies. Likewise, editors and reviewers value the presentation of empirical data (and significant findings) higher than, for example, the presentation of raw data such as annotated speech corpora and similar documentations.

 We are organizing a special issue for Revista da Abralin whose objective is to gather articles that contribute to the central principle of replication / reproduction of experimental studies in the area of linguistics. The focus should be on impact studies, i.e. studies that were or still are frequently cited well beyond the authors' own citation circles, not necessarily only those studies that directly led to influential theories).

Three types of submissions are welcome.

  1. Submissions that focus entirely on replication/reproduction. When designing such studies, authors are encouraged to work in collaboration with those author(s) of the original study to ensure that replication follows as closely as possible the original methods.
  2. Submissions that replicate a key aspect of a previous study and then add an own original piece of work on top, for example, in order to explain why the previous results could not be replicated or in order to advance or substantiate the previous results. This can be done by applying a different (measuring) method, by using different speaker or listener samples (e.g., with respect to language, age, or gender), or by following up on one of the open questions raised by the author(s) in the previous study.
  3. Submissions that present a speech, gesture, or language-data corpus and that make this resource available to the linguistics community.

All papers submitted to this special issue of Revista da Abralin should be pre-registered on the Open Science Framework website (https://osf.io/).

Submission deadline: December 31, 2020

Submission link: http://revista.abralin.org/index.php/abralin/submission/wizard

Author Guidelines and Submission Preparation Checklist are available here: http://revista.abralin.org/index.php/abralin/about/submissions

Guest Editors:

Miguel Oliveira, Jr. (Universidade Federal de Alagoas)

Oliver Niebuhr (University of Southern Denmark)

Back  Top

7-11Computer, Speech and Language, special issue on Voice Privacy
COMPUTER SPEECH AND LANGUAGE
 
Special issue on Voice Privacy  
 
Deadline: January 8, 2021
 
Recent years have seen mounting calls for the preservation of privacy when treating personal data. Speech falls within that scope because it encapsulates a wealth of personal information that can be revealed by listening or by automatic speech analysis and recognition systems. This includes, e.g., age, gender, ethnic origin, geographical background, health or emotional state, political orientations, and religious beliefs, among others. In addition, speaker recognition systems can reveal the speaker?s identity. It is thus of no surprise that efforts to develop privacy preservation solutions for speech technology are starting to emerge.
 
A few studies have tackled the formal definition of privacy preservation, the provision of suitable datasets, and the design of evaluation protocols and metrics based on user and attacker models. Other studies have addressed the development of privacy preservation methods which maximize the utility for users while defeating attackers. Current methods fall into four categories: deletion, encryption, anonymization, and distributed learning. Deletion methods aim to delete or obfuscate speech based on speech enhancement or privacy-preserving feature extraction for ambient sound analysis purposes. Encryption methods such as fully homomorphic encryption and secure multiparty computation can be used to implement all computations in the encrypted domain. Anonymization methods aim to suppress personal information but retain other information by means of noise addition, speech transformation, voice conversion, speech synthesis, or adversarial learning. Decentralized or federated learning methods aim to learn models (for, e.g., keyword spotting) from distributed data without accessing individual data points nor leaking information about them in the models.
 

This special issue solicits papers describing advances in privacy protection for speech processing systems, including theoretical developments, algorithms or systems.

Examples of topics relevant to the special issue include (but are not limited to):
  • formal models of speech privacy preservation,
  • privacy-preserving speech feature extraction,
  • privacy-driven speech deletion or obfuscation,
  • privacy-driven voice conversion,
  • privacy-driven speech synthesis and transformation,
  • privacy-preserving decentralized learning of speech models,
  • speech processing in the encrypted domain,
  • open resources, e.g., datasets, software or hardware implementations, evaluation recipes, objective and subjective metrics.
 
Submission instructions: 

Manuscript submissions shall be made through: https://www.editorialmanager.com/YCSLA/.

The submission system will be open early October. When submitting your manuscript please select the article type ?VSI: Voice Privacy?. Please submit your manuscript before the submission deadline.

All submissions deemed suitable to be sent for peer review will be reviewed by at least two independent reviewers. Once your manuscript is accepted, it will go into production, and will be simultaneously published in the current regular issue and pulled into the online Special Issue. Articles from this Special Issue will appear in different regular issues of the journal, though they will be clearly marked and branded as Special Issue articles.
Please see an example here: https://www.sciencedirect.com/journal/science-of-the-total-environment/special-issue/10SWS2W7VVV
Please ensure you read the Guide for Authors before writing your manuscript. The Guide for Authors and the link to submit your manuscript is available on the Journal?s homepage https://www.elsevier.com/locate/csl.

 
Important dates:

January 8, 2021: Paper submission
May 7, 2021: First review
July 9, 2021: Revised submission
September 10, 2021: Final decision
October 8, 2021: Camera-ready submission

 
Guest Editors:
Emmanuel Vincent, Inria
Natalia Tomashenko, Avignon Université
Junichi Yamagishi, National Institute of Informatics and University of Edinburgh
Nicholas Evans, EURECOM
Paris Smaragdis, University of Illinois at Urbana-Champaign
Jean-François Bonastre, Avignon Université
Back  Top

7-12CfP Computer, Speech and Language, Special Issue on Separation, 'Recognition, and Diarization of Conversational Speech'
Call for papers
 
Computer Speech and Language
 
Special Issue on Separation, Recognition, and Diarization of Conversational Speech

https://www.journals.elsevier.com/computer-speech-and-language/call-for-papers/call-for-papers-computer-speech-and-language-special-issue

 
Submission deadline: December 15, 2020
 
 
While great advances have been made in conversational automatic speech recognition in recent years, several fundamental problems remain before the goal of a richly annotated transcript of speech and speakers can be realized. The current special issue invites papers to discuss the robustness of speech processing in everyday environments, i.e., real-world conditions with acoustic clutter, where the number and nature of the sound sources is unknown and changing over time.
 
Relevant research topics include (but are not limited to):
  • Speaker identification and diarization
  • Speaker localization and beamforming
  • Single- or multi-microphone enhancement and separation
  • Robust features and feature transforms
  • Robust acoustic and language modeling
  • Traditional or end-to-end robust speech recognition
  • Training schemes: data simulation and augmentation, semi-supervised training
  • Robust speaker and language recognition
  • Robust paralinguistics
  • Cross-environment or cross-dataset performance analysis
  • Environmental background noise modelling.
In addition to traditional research papers, the special issue also hopes to include descriptions of successful conversational speech recognition systems where the contribution is more in the implementation than the techniques themselves as well as successful applications of conversational speech recognition systems.

The recently concluded sixth CHiME challenge serves as a focus for discussion in this special issue. The challenge considered the problem of conversational speech recognition and diarization in everyday home environments from multiple distant microphone arrays. It used a resychronized version of the Dinner Party speech data featured in CHiME-5 and added a new joint diarization and ASR task. Papers reporting evaluation results on the CHiME-6 dataset or on other datasets are equally welcome.


Submission instructions

Manuscript submissions shall be made through: https://www.editorialmanager.com/YCSLA/.

The submission system will be open in November. When submitting your manuscript please select the article type ?VSI:SeparateRecognizeDiarize?. Please submit your manuscript before the submission deadline.

All submissions deemed suitable to be sent for peer review will be reviewed by at least two independent reviewers. Once your manuscript is accepted, it will go into production, and will be simultaneously published in the current regular issue and pulled into the online Special Issue. Articles from this Special Issue will appear in different regular issues of the journal, though they will be clearly marked and branded as Special Issue articles. Please see an example here: https://www.sciencedirect.com/journal/science-of-the-total-environment/special-issue/10SWS2W7VVV

Please ensure you read the Guide for Authors before writing your manuscript. The Guide for Authors and the link to submit your manuscript is available on the Journal?s homepage https://www.elsevier.com/locate/csl.


Important dates:
  • Submission opens: November 16, 2020
  • Submission deadline: December 15, 2020
  • Acceptance deadline: September 1, 2021
  • Expected publication date: November 1, 2021

Guest editors
  • Michael Mandel, Brooklyn College, CUNY
  • Jon Barker, University of Sheffield
  • Jun Du, University of Science and Technology of China
  • Leibny Paola Garcia, Johns Hopkins University
  • Emmanuel Vincent, Inria
  • Shinji Watanabe, Johns Hopkins University
Back  Top

7-13Special issue of Brain Sciences: 'Motor Speech Disorders and Prosody'
Submissions are open for the Brain Sciences Special Issue entitled 'Motor Speech Disorders and Prosody', guest edited by Anja Lowit, Sónia Frota and Marina Vigário.
 
Manuscript submissions will be accepted until March 20, 2021.
Detailed information can be found at the Special Issue website: https://www.mdpi.com/journal/brainsci/special_issues/Motor_Speech_Disorders
Please kindly help us to spread the word.
 
Looking forward to your contributions,
Sónia Frota (and Anja Lowit and Marina Vigário)
 

 

Sónia Frota
Professora catedrática | Professor
Coordenadora Científica - CLUL | Scientific Coordinator - CLUL
Centro de Linguística da Universidade de Lisboa | Center of Linguistics of the University of Lisbon (CLUL)
 
 
https://www.researchgate.net/profile/Sonia_Frota2 
 


Faculdade de Letras da Universidade de Lisboa | School of Arts and Humanities
Alameda da Universidade 1600-214 Lisboa PORTUGAL
Telefone: 217 920 000 | www.letras.ulisboa.pt 
Back  Top

7-14CfP IEEE JSTSP Special Issue on Deep Learning for High Dimensional Sensing

 

Call for Papers
IEEE JSTSP Special Issue on

Deep Learning for High Dimensional Sensing

Sensing is the first step to perceive and understand the environment. We are living in a high-dimensional world and thus high-dimensional sensing (HDS) and signal processing play pivotal roles in many fields such as robotics and surveillance. The recent explosive growth of artificial intelligence has provided new opportunities and tools for computational and learning based sensor design. In many emerging real applications such as advanced driver assistance systems / automated driving systems, large-scale, highdimensional and diverse types of data need to be captured and processed with high accuracy and in a realtime manner. To address these challenges, it is highly desirable to develop new sensing techniques with high performance to capture high-dimensional data employing recent advances in deep learning (DL).

This special issue is devoted to DL for HDS, with the goals to highlight new research accomplishments and developments, open issues and promising new directions, related to system design, theory, algorithms and applications. This special issue will include high-quality novel contributions in this emerging field including but not limited to:

Topics of interest include, but are not limited to:
  • HDS systems (hyperspectral, multispectral, video, X-ray, MRI, ultrasound, SAR, Tomography, Terahertz and Radar, LIDAR, acoustic and speech).
  • Large field-of-view sensing and super resolution
  • Non-line-of-sight imaging.
  • Deep learning based reconstruction algorithm development for HDS.
  • Theoretical analysis and interpretability of deep learning methods for HDS systems.
  • Deep/reinforcement learning for HDS system design.
  • Object classification, detection, segmentation and/or recognition for HDS systems.
  • Deep learning for information fusion from diverse HDS systems.

Submission Guidelines

Prospective authors should follow the instructions given on the IEEE JSTSP webpages and submit their manuscript through the web submission system

Important Dates

  • Manuscript submissions due: October 15, 2021
  • First review completed: November 30, 2021
  • Revised manuscript due: January 15, 2022
  • Second review completed: February 28, 2022
  • Final manuscript due: April 15, 2022
  • Publication: June 2022

Guest Editors
Back  Top

7-15CfP IEEE Trans. on Multimedia (TMM) Special issue on Learning from Noisy Multimedia Data

Call for Papers
IEEE Transactions on Multimedia (TMM) Special Issue
on Learning from Noisy Multimedia Data

 

Summary


With the development of computing power and deep learning algorithms, we can process and apply millions or even hundreds of millions of large-scale data to train robust models. Nevertheless, constructing a million-scale dataset like ImageNet is time-consuming and labor-intensive. Fortunately, web data are rich and free resources. For arbitrary categories, the potential training data can be easily obtained from the web (e.g., search engines such as Google and Bing, Twitter, Instagram, and short video sharing applications). Moreover, with the development of the Internet, web data consist of much richer modality, such as text, audio, image, and video. It is consequently natural to leverage the large-scale yet noisy data on the web to automatically construct various types of datasets. However, there are two critical issues in the automatically collected datasets: ?label noise? and ?domain mismatch?. Learning directly from noisy web data tends to have poor performance.

This special issue serves as a forum for researchers all over the world to discuss their works and recent advances in learning from noisy web data. Both state-of-the-art articles, as well as comprehensive literature reviews, are welcome for submission. To provide readers of the special issue with an understanding of the most current issues in this field, we will invite one survey paper, which will undergo peer review. Papers addressing interesting real-world multimedia as well as computer vision applications are especially encouraged.
 

Scope


The special issue seeks original contributions which address the challenges in learning from noisy multimedia data. Possible topics include but are not limited to:
  • Webly supervised visual classification, detection, segmentation, and feature learning
  • Large-scale/web-scale noisy data learning systems
  • Label noise in deep learning, theoretical analysis, and application
  • Automatic image dataset construction and application
  • Multi-modality theoretical analysis and application
  • Data augmentation theoretical analysis and application
  • Transfer learning across labeled and web data
  • New datasets and benchmarks for webly supervised learning

Submission Procedure


Papers should be formatted according to the IEEE Transactions on Multimedia guidelines for authors. By submitting/resubmitting your manuscript to these Transactions, you are acknowledging that you accept the rules established for publication of manuscripts, including an agreement to pay all over-length page charges, color charges, and any other charges and fees associated with the publication of the manuscript.

Manuscripts (both 1-column and 2-column versions are required) should be submitted electronically through the online IEEE manuscript submission system. All submitted papers will go through the same review process as the regular TMM paper submissions. Referees will consider originality, significance, technical soundness, clarity of exposition, and relevance to the special issue topics above

Important Dates

  • Paper submission due: January 31, 2021
  • First review notification: March 15, 2021
  • Revision due: May 15, 2021
  • Second review notification: June 15, 2021
  • Final version due: August 30, 2021
  • Publication: Early 2022

Guest Editors
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