ISCA - International Speech
Communication Association


ISCApad Archive  »  2020  »  ISCApad #267  »  Journals

ISCApad #267

Thursday, September 10, 2020 by Chris Wellekens

7 Journals
7-1special issue of Language and Speech on sociolinguistic prosodic variation

Special issue of Language and Speech

 

The goal of this special issue of Language and Speech is to highlight recent work exploring sociolinguistic variation in prosody. The papers will be based in part on talks and poster presentations from the recent “Experimental and Theoretical Advances in Prosody” conference (ETAP4, etap4.krisyu.org) which featured a special theme entitled: “Sociolectal and dialectal variability in prosody.” Note, however, that this is an open call and submissions are not restricted to papers presented at the conference.

 

As in many language fields, studies of prosody have focused on majority languages and dialects and on speakers who hold power in social structures. The goal of this special issue is to diversify prosody research in terms of the languages and dialects being investigated, as well as the social structures that influence prosodic variation. The issue brings together prosody researchers and researchers exploring sociological variation in prosody, with a focus on the prosody of marginalized dialects and prosodic differences based on gender and sexuality.

 

We invite proposals for papers that will:

• Establish the broad questions in sociolinguistics that would especially benefit from prosodic research

• Address the theoretical and methodological challenges and opportunities that come with studying sociolinguistic prosodic variation

• Share best practices for engaging in prosodic research of understudied languages and social groups to address linguistic bias

We especially encourage proposals for papers that focus on the prosody of marginalized dialects and prosodic differences based on gender and sexuality.

 

The editors of the special issue will be Meghan Armstrong-Abrami, Mara Breen, Shelome Gooden, Erez Levon, and Kristine Yu.  The editors will review submitted paper proposals and then invite authors of selected proposals to submit full papers. Each invited paper will be handled by one of the editors and reviewed by 2-3 additional reviewers. Based on the reviews, the editors plan to accept 10-12 papers for publication in this special issue. Please note that publication is not guaranteed in this special issue. Invited papers will undergo the standard Language and Speech review process and be subject to Language and Speech author guidelines (https://us.sagepub.com/en-us/nam/journal/language-and-speech#submission-guidelines). Invited papers can be short reports or full reports (see author guidelines, section 1.2).

 

Paper proposals in PDF file format must be sent to etap4umass@gmail.com by May 15, 2019. Proposals must not be more than 1 page (with an additional page allowed for figures, examples, and references). Authors of selected proposals will be invited to submit their full papers, which will be due by 12/15/19. Acceptance/rejection notifications will be sent in early 2020 with editorial comments. We are hoping to submit our final proofs to the journal by summer 2020.

 

Back  Top

7-2CfP. Special issue Speech Communication: Pluricentric Languages in Speech Technology

Call for papers: Pluricentric Languages in Speech Technology

Pluricentric languages (PLCLs) are a common type among the languages of the world. Presently 43 languages have been identified to belong to this category. Languages like English, Spanish, Portuguese, Bengali, Hindi, Urdu etc. fall into this category. A language is identified as pluricentric if it is being used in at least two nations where it is also having an official function and if it is forming national varieties of their own with specific linguistic and pragmatic features. In addition to the variation on the level of national standard varieties, there is also so called “second level variation” on a regional and local level that is often being used in diglossic speech situations where code switching is a salient feature with two or more varieties being used within the same utterance. The amount of linguistic variation in pluricentric languages is considerable and poses a challenge for speech recognition in particular and human language technology in general.

The topic of pluricentric languages overlaps in some aspects with the topic of low-resourced languages. In contrast to “low-resourced” languages, pluricentric languages may already have plenty of resources (e.g., English, French, German), but variant sensitive or variant-independent technology is likely to be absent. In contrast to activities in the field of dialect recognition, the “non-dominant” varieties of pluricentric languages are the standard language in the respective countries and thus are also printed and spoken in media, parliaments and juridical texts.

The motivation for this special issue is the observation that pluricentric languages have so far mainly been described linguistically but not sufficiently been dealt with in the field of speech technology. This is particularly the case with the so-called “non-dominant varieties”. Given the current state of research in the field, we are especially interested in contributions which:

investigate methods for creating speech and language resources, with a special focus on “non-dominant varieties” (e.g., Scots, Saami, Karelian Finnish, Tadczik, Frisian as well as diverse American and African languages: Aymara, Bamabara, Fulfulde, Tuareg, etc.).

develop speech technologies such as speech recognition, text-to-speech and speech-to-speech for the national varieties of pluricentric languages; on the level of standard varieties and on the level of so-called “informal speech”.

investigate novel statistical methods for speech and language technology needed to deal with small data sets.

study the (automatic) processing of speech for code-switched speech in national varieties of pluricentric languages.

investigate methods on how to use speech technology to aid sociolinguistic studies.

present empirical perception and production studies on the phonetics and phonology of national varieties of pluricentric languages.

present empirical perception and production studies on learning a pluricentric language as a second language and on developing computer aided language learning (CALL) tools for pluricentric languages.

study effects on speech technology on language change for pluricentric languages (e.g., compare developments of non-dominant varieties in comparison of dominant varieties for which speech and language technologies are available).

This special issue is inspired by the Sattelite Workshop of Interspeech “Pluricentric Languages in Speech Technology” to be held in Graz on September 14, 2019 (http://www.pluricentriclanguages.org/ndv-interspeech-workshop-graz-2019/?id=0). The special issue invites contributions from participants of the workshop as well as from others working in related areas. Papers of interdisciplinary nature are especially welcome! Manuscript submission to this Virtual Special Issue is possible between December 1, 2019 and November 30, 2020.

 

 

Editors:

Rudolf Muhr (University of Graz, Austria), rudolf.muhr@uni-graz.at

Barbara schuppler (Graz University of Technology, Austria), b.schuppler@tugraz.at

Tania Habib (University of Engineering and Technology Lahore, Pakistan), tania.habib@uet.edu.pk

Back  Top

7-3CfP IEEE SPM Special issue: Non-Convex Optimization for Signal Processing and Machine Learning

CALL FOR PAPERS

IEEE Signal Processing Magazine Special Issue on

Non-Convex Optimization for Signal Processing and Machine Learning
 

 

Optimization is now widely reckoned as an indispensable tool in signal processing and machine learning. Although convex optimization remains a powerful, and is by far the most extensively used, paradigm for tackling signal processing and machine learning applications, we have witnessed a shift in interest to non-convex optimization techniques over the last few years. On one hand, many signal processing and machine learning applications-such as dictionary recovery, low-rank matrix recovery, phase retrieval, and source localization-give rise to well-structured non-convex formulations that exhibit properties akin to those of convex optimization problems and can be solved to optimality more efficiently than their convex reformulations or approximations.

On the other hand, for some contemporary signal processing and machine learning applications-such as deep learning and sparse regression-the use of convex optimization techniques may not be adequate or even desirable. Given the rapidly-growing yet scattered literature on the subject, there is a clear need for a special issue that introduces the essential elements of non-convex optimization to the broader signal processing and machine learning communities, provides insights into how structures of the non-convex formulations of various practical problems can be exploited in algorithm design, showcases some notable successes in this line of study, and identifies important research issues that are motivated by existing or emerging applications. This special issue aims to address the aforementioned needs by soliciting tutorial-style articles with pointers to available software whenever possible. 

Topics of interest include (but are not limited to):
  • optimization fundamentals, including algorithm design and analysis techniques for generic and structured problems (e.g., difference-of-convex optimization, mixed-integer optimization, non-convex non- Lipschitz optimization, non-convex non-smooth optimization), parallel and distributed non-convex methods, and software toolboxes
  • big data analytics
  • blind demixing and deconvolution
  • computer vision and image processing applications
  • deep learning
  • localization
  • massive MIMO
  • phase retrieval
  • statistical estimation
  • structured matrix/tensor decomposition, such as low-rank matrix recovery and non-negative matrix/tensor factorization, with applications
Submission Process:

To enhance readability and appeal for a broad audience, prospective authors are encouraged to use an intuitive approach in their presentation; e.g., by using simple instructive examples, considering special cases that show insights into the ideas, and using illustrations as far as practicable.

Prospective authors should submit their white papers through the ScholarOne ManuscriptsTM system. Further guidelines and information on paper submission can be found on the SPS website.

Important Dates:  

White paper due: August 1, 2019
Invitation notification: September 1, 2019
Manuscript due: November 1, 2019
First review to authors: January 1, 2020

Guest Editors:


Back  Top

7-4IEEE STSP Special issue: Deep Learning for Multi-modal Intelligence across Speech, Language, Vision, and Heterogeneous Signals (extended deadline)

Call for Papers
IEEE JSTSP Special Issue on

Deep Learning for Multi-modal Intelligence across
Speech, Language, Vision, and Heterogeneous Signals

 

Extended deadline to September 15th


In the past years, thanks to the disruptive advances in deep learning, significant progress has been made in speech processing, language processing, computer vision, and applications across multiple modalities. Despite the superior empirical results, however, there remain important issues to be addressed. Both theoretical and empirical advancements are expected to drive further performance improvements, which in turn would generate new opportunities for in-depth studies of emerging novel learning and modeling methodologies. Moreover, many problems in artificial intelligence involve more than one modality, such as language, vision, speech and heterogeneous signals. Techniques developed for different modalities can often be successfully cross-fertilized. Therefore, it is of great interest to study multimodal modeling and learning approaches across more than one modality. The goal of this special issue is to bring together a diverse but complementary set of contributions on emerging deep learning methods for problems across multiple modalities. The topics of this special issue include but not limit to the following:

Topics of interest in this special issue include (but are not limited to):

  • Fundamental problems and methods for processing multi-modality data including language, speech, image, video, and heterogeneous signals
  • Pre-training, representation learning, multitask learning, low-shot learning, and reinforcement learning of multimodal problems across natural language, speech, image, and video
  • Deep learning methods and applications for cross-modalities, such as image captioning, visual question answering, visual story-telling, text-to-image synthesis, vision-language navigation, etc.
  • Evaluation metrics of multimodal applications


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

Back  Top

7-5CfP 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

7-6Special issue of the TAL journal on 'NLP and health'

Special issue of the TAL journal on 'NLP and health'

tal-61-2.sciencesconf.org


The medical application domain and the discipline of Natural Language Processing have been interacting for a good half century now, to mutual benefit. NLP techniques have helped in medical knowledge discovery and clinical practice improvements.  At the same time, the medical field has contributed meaningful tasks, sizeable document collections (e.g., MIMIC for patient records, MEDLINE for scientific abstracts), and detailed lexical resources (UMLS), and these have helped advancements in the discipline of NLP in general.

Language is prevalent throughout the care process. It is used to encode institutional knowledge and health information, patient language productions can be analyzed for diagnosis (speech and/or voice disorders, language disorders, mental illnesses), it conveys patient and health professional interactions (consultations, consensus meetings), and also encodes clinical descriptions of pathologies and their management from the perspective of patients and health professionals (social networks, patient records). These language productions all address the specialiazed theme of health while exhibiting great diversity in terms of medium (written or spoken language), register (written material published in journals, professional note-taking in clinical documents, spontaneous production on social networks), language (English for literature, any language for other types of documents), etc.

As computer science goes through rapid changes (deep learning, big data, internet of things), and the medical field is seeing its own opportunities (precision medicine, drug discovery) and pressures (chronic diseases, an aging population), interactions between these fields are more relevant than ever.

This special issue of TAL aims to provide an overview of current NLP research on all aspects of health, including fundamental work and applications.

Authors are invited to submit papers on all aspects of NLP for health, in particular regarding, but not limited
to, the following issues and tasks:

- general vs. in-domain pre-trained language models
- general pre-trained vs. in-domain embeddings
- analytics of social media related to health
- analysis of speech for medical purposes: speech pathology, interactions between medical professionals and patients
- accessibility of health information: NLP for improving text comprehension, text simplification, machine translation, systematic review support
- Automatic processing in the context of speech and language impairment: Augmentative and Alternative Communication (AAC) solutions (from or to speech, text, symbols, sign language), Automatic characterization of disorders, assessment of their severity, decision support
- Conversational Agents (CA) in health and medical care (e-learning, virtual assistants, ...)

We particularly welcome submissions reporting work on languages other than English and inclusive of vulnerable groups.

IMPORTANT DATES

- Submission deadline: March 15, 2020?
- Notification to the authors after the first review May 30 2020
- Notification to the authors after the second review: mid-July 2020
- Final version: October 2020
- Publication: December 2020

LANGUAGE

Manuscripts may be submitted in English or French. French-speaking authors are requested to submit their contributions in French.

JOURNAL

Traitement Automatique des Langues is an international journal published since 1960 by ATALA (Association pour le traitement automatique des langues) the French association for NLP with the support of CNRS. It is now published online, with an immediate open access to published papers, and annual print on demand. This does not
change its editorial and reviewing process.

FORMAT

Papers must be between 20 and 25 pages, references and appendices included (no length exemptions are possible). Authors who intend to submit a paper are encouraged to click the menu item 'Paper submission' (PDF format). To do so, they will need to have an account, or create it, on the sciencesconf platform (go to 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 http://tal-61-2.sciencesconf.org/, connect to the account and upload the submission.

From now on, TAL will perform double-blind review: it is thus necessary to anonymize the manuscript and the name of the pdf file. Style sheets are available for download on the Web site of the journal (http://www.atala.org/English-style-files).


SPECIAL ISSUE EDITORIAL BOARD

Guest editors:
- Aurélie Névéol, LIMSI-CNRS/Université Paris-Saclay, France
- Berry de Bruijn, Conseil national de recherches Canada
- Corinne Fredouille, LIA/Avignon Université, France

 

Members:
- Asma Ben Abacha, National Library of Medicine, États-Unis
- Gabriel Bernier-Colborne, Conseil national de recherches Canada
- Sandra Bringay, LIRMM, Université de Montpellier, France
- Leonardo Campillos Llanos, Universidad de Madrid, Espagne
- Jérôme Farinas, IRIT, Université de Toulouse, France
- Graciela Gonzalez-Hernandez, University of Pennsylvania, États-Unis
- Natalia Grabar, STL-CNRS, Université de Lille, France
- Julia Ive, King?s College, London, Royaume-Uni
- Svetlana Kiritchenko, Conseil national de recherches Canada
- Hongfang Liu, Mayo Clinic, États-Unis
- Stan Matwin, Dalhousie University, Halifax NS, Canada
- Timothy Miller, Harvard University,  États-Unis
- Maite Oronoz, Universidad del País Vasco, Espagne
- François Portet, LIG, Université de Grenoble, France
- Laurianne Sitbon, Queensland University of Technology, Australie
- Sumithra Vellupilai, King?s College, London, Royaume-Uni
- Meliha Yetisgen, University of Washington, États-Unis

 

Back  Top

7-7IEEE JSTSP Special issue on Reconstruction of Audio from Incomplete or Highly Degraded Observations

Call for Papers
IEEE JSTSP Special Issue on

Reconstruction of Audio from Incomplete
or Highly Degraded Observations

 
Deadline Extended: May 1, 2020
 

The restoration of audio content, in particular speech and music from degraded observations, is a challenging and long-standing problem in audio processing. In particular this holds for severe degradations and incomplete observations. Traditional restoration techniques are often not applicable or perform poorly in this case. The advent of sparse signal processing in the beginning of this century and, even more recently, of (deep) machine learning has opened wide new research and design opportunities for audio restoration, among many other signal processing problems. With the aid of such contemporary tools, researchers have recently been able to achieve unprecedented success in recovering or significantly improving quality of severely degraded audio. As the field advances very quickly, the potential for improvement, as well as exploration, is hardly exhausted.

Audio restoration addresses a large number of important degradation scenarios. Further, audio restoration can be performed with varied tools. The proposed issue will serve both as a comprehensive primer on the state-of-the-art, and a showcase of current developments within the field, targeting newcomers as well as already experienced researchers.

Topics of interest in this special issue include (but are not limited to):

  • Restoration problems:
    packet loss concealment; inpainting; declipping; dequantization; phase recovery; bandwidth extension; coding artifact removal; compressive sampling recovery; dynamic range decompression; reconstructing audio signals from features,
  • Methodological frameworks:
    time-frequency representations; (non-)convex optimization; operator and dictionary learning; nonnegative matrix/tensor factorization; (end-to-end) artificial neural networks; generative networks (e.g., generative adversarial nets and variational autoencoders); graph signal processing; psychoacoustics.

Excellent articles that cannot be accommodated in the special issue will be automatically transferred (without re-submission) and considered for regular publication in IEEE/ACM TASLP.
 
This special issue encourages reproducible research: authors are invited to provide their code and data, to use available material for benchmarking (e.g. SMALL dataset), and to contribute by any means (e.g., high-quality datasets and code, challenges) to the sustainability, the reproducibility and the reliability of the research works in the proposed topics.

Accepted articles are immediately published as Early Access and do not wait until the entire special issue is closed.

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


 

Important Dates

 

  • Manuscript submission:  May 1, 2020 (Extended)

  • Decision notification:  July 1, 2020

  • Revised manuscript due:  August 1, 2020

  • Second reviews completed:  September 15, 2020

  • Final manuscript due:  November 1, 2020

 

Guest Editors

 




Back  Top

7-8CFP: Special Issue of JMUI on 'Behavior and Usability Analysis for Multimodal User Interfaces' i

CFP: Special Issue on ?Behavior and Usability Analysis for Multimodal User Interfaces? in JMUI

Joint analysis of different modalities of user inputs such as text, speech, voice, facial expressions, gesture, and physiological signals, is an important area of research, and highly beneficial in more natural and effective forms of intelligent human computer interaction. With the recent dramatic advances in machine learning, signal processing, computer vision, and natural language processing, variety of multimodal applications increases every day. Application areas include healthcare, autonomous driving, robotics, sports analytics, neuromarketing, psychological and physiological assessment, surveillance, gaming, and augmented/virtual reality. Consequently, in the era of intelligent systems, reliable interpretation of human behavior and detailed analysis of usability for multimodal user interfaces gain further importance.  


We solicit contributions to a special issue of the Journal on Multimodal User Interfaces on ?Behavior and Usability Analysis for Multimodal User Interfaces.? For this special issue, we welcome technical and empirical studies that focus on (a) interpretation and modeling of behavioral patterns, and (b) analysis and assessment of usability for multimodal human computer interaction. The topics include, but are not restricted to:

- Usability analysis
- User-centered interaction
- Human activity analysis
- Social signal processing
- Facial expression and gesture recognition
- Face and body tracking
- Speech recognition and voice analysis
- Text analysis
- Psychological and physiological assessment
- Multimodal fusion
- Spatio-temporal dynamics of actions and behavior
- Benchmarking studies on novel databases


SUBMISSIONS:
Submissions must represent original material. Papers are accepted for review with the understanding that the same work has been neither submitted to, nor published in, another journal or conference. All manuscripts will undergo a rigorous review process. Please indicate in your cover letter that you are submitting to the special issue. The authors are required to follow the Submission Guidelines of the Journal on Multimodal User Interfaces:
https://www.springer.com/journal/12193/submission-guidelines

IMPORTANT DATES:
Deadline for paper submission: 10 May 2020
Notification of review outcome: 5 July 2020
Camera-ready version of accepted papers: 9 August 2020
Estimated publication date: Autumn 2020  

EDITOR IN CHIEF:
Jean-Claude Martin, LIMSI/CNRS - University Paris South XI

GUEST EDITORS:
Hamdi Dibeklioglu, Bilkent University
Elif Surer, Middle East Technical University
Albert Ali Salah, Utrecht University
Thierry Dutoit, University of Mons

To submit a manuscript, visit https://www.springer.com/journal/12193


For more information contact:
Asst. Prof. Dr. Hamdi Dibeklioglu
Department of Computer Engineering,
Bilkent University
06800 Bilkent - Ankara, Turkey
phone: +90 (312) 290 1187
home: http://www.cs.bilkent.edu.tr/~dibeklioglu/
e-mail: dibeklioglu@cs.bilkent.edu.tr
Back  Top

7-9Special issue on Voice Privacy, Computer, Speech and Language
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

7-10Special 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

7-11Special 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

7-12Computer 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

7-13CfP: 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

7-14TAL 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

7-15Special 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

7-16CfP 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

7-17Call 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

7-18Computer, 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



 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