Special Issue on

Far-Field Speech Processing in the Era of Deep Learning
Speech Enhancement, Separation and Recognition

Far-field speech processing has become an active field of research due to recent scientific advancements and its widespread use in commercial products. This field of research deals with speech enhancement and recognition using one or more microphones placed at a distance from one or more speakers. Although the topic has been studied for a long time, recent successful applications (starting with Amazon Echo) and challenge activities (CHiME and REVERB) greatly accelerated progress in this field. Concurrently, deep learning has created a new paradigm that has led to major breakthroughs both in front-end signal enhancement, extraction, and separation, as well as in back-end speech recognition. Furthermore more deep learning provides a means of jointly optimizing all components of far-field speech processing in an end-to-end fashion. This special Issue is a forum to gather the latest findings in this very active field of research, which is of high relevance for the audio and acoustics, speech and language, and machine learning for signal processing communities. This issue is an official post-activity of the ICASSP 2018 special session 'Multi-Microphone Speech Recognition' and the 5th CHiME Speech Separation and Recognition Challenge (CHiME-5 challenge).

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

Guest Editors

• Shinji Watanabe, Johns Hopkins University, USA
• Shoko Araki, NTT, Japan
• Michiel Bacchiani, Google, USA
• Reinhold Haeb-Umbach, Paderborn University, Germany
• Michael L. Seltzer, Facebook, USA

Important Dates

• Submission deadline November 10, 2018
• 1st review completed: January 15, 2019
• Revised manuscript due: March 15, 2019
• 2nd review completed: May 15, 2019
• Final manuscript due: June 15, 2019
• Publication: August 2019

Back

Top

IEEE J-STSP Special Issue on

Acoustic Source Localization and Tracking
in Dynamic Real-life Scenes

Summary: Acoustic source localization is a well-studied topic in signal processing, but most traditional methods incorporate simplifying assumptions such as a point source, free-field propagation of the sound wave, static acoustic sources, time-invariant sensor constellations, and simple noise fields. However, these assumptions may be seriously violated in a range of emerging applications, such as audio recording with mobile devices (e.g. cell phones, extreme cameras, and robots), video conferencing on the go, and recording for 3D reproduction and virtual reality. In these applications, the environment is extremely challenging, with spatially distributed sources, reverberation, complex noise fields, multiple concurrent speakers, interferences, and time-varying sources and sensors positions.

The proposed special issue aims to present recent advances in the development of signal processing methods for localization and tracking of acoustic sources and the associated theory and applications. To address the challenges raised by the real-life environment, novel methods that use modern array processing, speech processing and data inference tools, become a necessity.

As these challenges involve both audio processing and sensor arrays, this proposal is timely and relevant to researchers from both acoustic signal processing domain and array processing domain. The guest editors are therefore coming from both communities. It comprises of current and past chairs of the respective technical committees (Audio and Acoustic Signal Processing ? AASP and Sensor and Sensor Array and Multichannel ? SAM TCs). This special issue proposal follows successful special sessions in major conferences: 'Learning-based Sound Source Localization and Spatial Information Retrieval' ICASSP2016), 'Speaker localization in dynamic real-life environments? (ICASSP2017), ?Acoustic Scene Analysis and Signal Enhancement using Microphone Array? (EUSIPCO2017), ?Acoustical Signal Processing for Hearables? (EUSIPCO2017).

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

Back

Top

Topical Issue on Intelligent Methods for Textual Information Retrieval
============================
Call for Papers: www.degruyter.com/page/1831
Submission deadline: 20th February 2019
============================
EDITED BY
Guest Editors:
Adrian-Gabriel Chifu, Aix-Marseille Université, France
Sébastien Fournier, Aix-Marseille Université, France
Advisory Editor:
Patrice Bellot, Aix-Marseille Université / CNRS, France
============================
DESCRIPTION
Machine learning approaches for intelligent text mining and retrieval are actively
studied by researchers in natural language processing, information retrieval and other
related fields. While supervised methods usually attain much better performance than
unsupervised methods, they also require annotated data which is not always available or
easy to obtain. Hence, we encourage the submission of supervised, unsupervised or hybrid
methods for intelligent text retrieval tasks. Methods studying alternative learning
paradigms, e.g. semi-supervised learning, weakly-supervised learning, zero-shot learning,
but also transfer learning, are very welcome as well.
This thematic special issue covers three research areas: natural language processing,
computational linguistics and information retrieval. The submissions may address, but are
not limited to, the following topics:
?        information retrieval
?        information extraction
?        query processing
?         word sense disambiguation/discrimination
?         machine learning in NLP
?         sentiment analysis and opinion mining
?         contradiction and controversy detection
?         social media
?         summarization
?         text mining
?         text categorization and clustering
The submitted papers will undergo peer review process before they can be accepted.
Notification of acceptance will be communicated as we progress with the review process.
============================
HOW TO SUBMIT
Before submission authors should carefully read the Instruction for Authors:
www.degruyter.com/view/supplement/s22991093_Instruction_for_Authors.pdf
Manuscripts can be written in TeX, LaTeX (strongly recommended) - the journal?s LATEX
template. Please note that we do not accept papers in Plain TEX format. Text files can be
also submitted as standard DOCUMENT (.DOC) which is acceptable if the submission in LATEX
is not possible. For an initial submission, the authors are strongly advised to upload
their entire manuscript, including tables and figures, as a single PDF file.

All submissions to the Topical Issue must be made electronically via online submission
system Editorial Manager:
www.editorialmanager.com/opencs/
All manuscripts will undergo the standard peer-review procedure (single blind, at least
two independent reviews). When entering your submission via online submission system
please choose the article type ?TI on Information Retrieval?.

The deadline for submission is 20th February 2019, but individual papers will be reviewed
and published online on an ongoing basis.

Contributors to the Topical Issue will benefit from:
?        NO submission and publication FEES
?         indexation by Clarivate Analytics - Web of Science (ESCI) and SCOPUS
?         fair and constructive peer review provided by experts in the field
?         no space constraints
?         convenient, web-based paper submission and tracking system ? Editorial Manager
?         free language assistance for authors from non-English speaking regions
?         fast online publication upon completing the publishing process
?         better visibility due to Open Access
?         long-term preservation of the content (articles archived in Portico)
?         extensive post-publication promotion for selected papers
In case of any questions please contact Dr. Justyna ?uk, Managing Editor,
Justyna.Zuk@degruyteropen.com.We are looking forward to your submission.

Back

Top

Special Issue on Data Science:

Machine Learning for Audio Signal Processing

Audio signal processing is currently undergoing a paradigm change, where data-driven machine learning is replacing hand-crafted feature design. This has led some to ask whether audio signal processing is still useful in the 'era of machine learning.' There are many challenges, new and old, including the interpretation of learned models in high dimensional spaces, problems associated with data-poor domains, adversarial examples, high computational requirements, and research driven by companies using large in-house datasets that is ultimately not reproducible.

This special issue aims to promote progress, systematization, understanding, and convergence of applying machine learning in the area of audio signal processing. Specifically, we are interested in work that demonstrates novel applications of machine learning techniques in the area of sound and music signal processing, as well as methodological considerations of merging machine learning with audio signal processing. We seek contributions in, but not limited to, the following topics:

• audio information retrieval using machine learning;
• audio synthesis with given contextual or musical constraints using machine learning;
• audio source separation using machine learning;
• audio transformations (e.g., sound morphing, style transfer) using machine learning;
• unsupervised learning, online learning, one-shot learning, reinforcement learning, and incremental learning for audio;
• applications/optimization of generative adversarial networks for audio;
• cognitively inspired machine learning models of sound cognition;
• mathematical foundations of machine learning for audio signal processing.

This call addresses audio signal processing for speech, acoustic scenes, and music.

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

Important Dates

• Submission deadline: October 1, 2018
• 1st review completed: December 1, 2018
• Revised manuscript due: February 1, 2019
• 2nd review completed: March 1, 2019
• Final manuscript due: April 1, 2019
• Publication: May 2019

Guest Editors

• Abeer Alwan, University of California Los Angeles, USA
• Bo Li, Google, USA
• Juhan Nam, Korea Advanced Institute of Science and Technology, Korea
• Hendrik Purwins, Aalborg University Copenhagen, Denmark
• Ariya Rastrow, Amazon, USA
• Bob L. Sturm, KTH Royal Institute of Technology, Sweden

Back

Top

APPEL À CONTRIBUTIONS

Revue TIPA n°35, 2019
Travaux interdisciplinaires sur la parole et le langage

https://journals.openedition.org/tipa/

Emo-langages : Vers une approche transversale des langages dans leurs dynamiques émotionnelles et créatives

Éditrice invitée

Françoise Berdal-Masuy
ECLE (Emotion and Creativity in Language Education)

Les émotions font, depuis une petite vingtaine d’années, l’objet de l’attention des chercheurs dans de nombreuses disciplines jusqu’à donner naissance à un nouveau domaine de recherche, celui des « sciences affectives » (Sander, 2015). Les propositions du neuroscientifique et philosophe Antonio Damasio (1995) sur les liens entre raison et émotions ont contribué à la prise de conscience de la synergie de celles-ci dans la communication, y compris l’apprentissage et l’enseignement. En 2011, le linguiste Christian Plantin publie « Les bonnes raisons des émotions », qui va stimuler de nouvelles approches dans les sciences du langage, désormais attentives à mettre en lumière le rôle « raisonnable ou raisonné » joué par les émotions dans le discours. De nombreux événements scientifiques consacrés à ce sujet durant la seule année académique 2017-2018 témoignent de cet intérêt : « Emotissage : Affects dans l’enseignement-apprentissage des langues » du 4 au 7 juillet 2017 à Louvain-la-Neuve (Belgique), « Affect in language » le 2 février 2018 à Helsinki (Finlande), « Affects, émotions et expressivité en discours spécialisés » le 2 mars 2018 à Lyon (France), « Langage et émotions » les 25 et 26 juin 2018 à Montpellier (France) et « Language, Education and Emotions » du 26 au 28 novembre 2018 à Anvers (Belgique) (liste non exhaustive). Le thème est appelé à évoluer constamment.

Réhabilités par les neurosciences, les affects et leur dimension culturelle sont ainsi considérés comme partie prenante de la construction de notre représentation du monde. Cet essor de la recherche sur les émotions / affects dépasse largement le plan méthodologique et théorique, il va de pair avec les mutations de la société et l’incapacité des modèles existants à y répondre. Une deuxième dimension est dès lors convoquée, rendue nécessaire par un monde complexe et changeant, celle de la créativité afin que, conjuguée à la dimension affective, elle rende possible l’innovation (Lison, 2018) qui donne vie au futur.

C’est donc la triade « émotions », « créativité » et « langages » et l’étude de leur interaction dynamique qui fait l’objet de ce numéro.

Les émotions peuvent être décrites en psychologie selon deux approches principales : soit de façon catégorielle en distinguant les émotions primaires (la joie, la tristesse, la surprise, etc.) des émotions secondaires en lien avec la relation sociale (la honte, la jalousie, le bonheur, etc.), soit selon une approche dimensionnelle sur deux axes : celui de la valence, qui peut être positive comme négative, et celui du niveau d’éveil, qui peut correspondre à une faible ou à une forte activation physiologique (Botella, 2015).

Quant à la créativité, il faut se tourner vers l’approche multivariée en psychologie différentielle de Lubart (2015) pour découvrir que, fruit de plusieurs facteurs (cognitif, conatif, environnemental et émotionnel), elle est définie comme la capacité à produire un produit ou un processus « nouveau » et « adapté » au contexte, le facteur émotionnel jouant un rôle important dans le processus créatif (Capron Puozzo, 2015).

Enfin, le terme « langage » comprend ici à la fois le langage verbal et corporel. « Et…, pour autant que le réductionnisme n’entraîne pas les neurosciences, celles-ci pourraient bien contribuer à expliciter davantage comment le corps vient à se nouer au langage, ou vice-versa » (Crommelinck & Lebrun, 2017, 173). Quant à Antonio Damasio, il énonce ceci : « Notre organisme contient un corps proprement dit, un système nerveux et un esprit provenant de ces deux éléments » (Damasio, 2017, 100). Il est opportun de prendre aussi en compte la réflexion des artistes de la scène (comédiens et danseurs), dans un dépassement du clivage sciences et arts via les corps qui traduisent extraordinairement le partage des émotions (Pairon, 2018).

Plusieurs travaux ont mis en évidence les liens entre émotions et langues (Dewaele, 2010 ; Pavlenko, 2014 ; Berdal-Masuy & Pairon, 2015 ; Baider, Cislaru et Coffey, 2015). Avec ce numéro, nous invitons, les membres de disciplines différentes (psychologie, neurosciences, sociologie, pédagogie, sciences du langage, champ de la réhabilitation et arts de la scène) à mobiliser des méthodologies plurielles et à partager leur apport et expérience sous forme de texte ou/ et vidéo afin de stimuler des connexions transversales originales entre émotions, créativité et langages, pour une approche stimulante des dynamiques à l’œuvre entre -et au cœur de- ces trois concepts.

Les articles soumis à la revue TIPA sont lus et évalués par le comité de lecture de la revue. Ils peuvent être rédigés en français ou en anglais et présenter des images, photos et vidéos (voir « consignes aux auteur(e)s »). Une longueur entre 10 et 12 pages est souhaitée pour chacun des articles, soit environ 35 000 - 48 000 caractères ou 6 000 - 8 000 mots (bibliographie, tableaux et annexes inclus). Les auteur(e)s sont prié(e)s de fournir un résumé de l’article dans la langue de l’article (français ou anglais ; entre 700 - 1300 caractères) ainsi qu’un résumé long d’environ deux pages (environ 8 000 - 9 000 caractères, dans l’autre langue : français si l’article est en anglais et vice versa), et 5 mots-clés dans les deux langues (français-anglais).

Échéancier

·         2 juillet 2018 : premier appel à contribution

·         15 septembre 2018 : second appel à contribution

·         15 décembre 2018 : soumission de l’article (version 1)

·         15 février 2019 : retour du comité scientifique ; acceptation, proposition de modifications (de la version 1) ou refus

·         15 mars 2019 : soumission de la version modifiée (version 2)

·         15 mai 2019 : retour du comité (concernant la version finale)

·         15 juin 2019 : parution

Instructions pour les auteur(e)s

Merci d’envoyer 3 fichiers sous forme électronique à : tipa@lpl-aix.fr et francoise.masuy@uclouvain :

- un fichier en .doc contenant le titre, le nom et l’affiliation de l’auteur (des auteurs)
- deux fichiers anonymes, l’un en format .doc et le deuxième en .pdf.

Pour la transcription des énoncés traduits en langue des signes, nous vous suggérons la convention suivante.
Pour davantage de détails, veuillez consulter la page des « consignes aux auteur(e)s ».


Références bibliographiques

Baider, F., Cislaru, G., & Coffey, S. 2015. Apprentissage, enseignement et affects. Le langage et l’homme. L1.

Berdal-Masuy, F., & Pairon, J. 2015. Affects et acquisition des langues. Le langage et l’homme. L2.

Botella, M. 2015. « Les émotions en psychologie : définitions et descriptions ». Dans Le langage et l’homme. L(2), 9-22.

Capron Puozzo, I. 2015. « Emotions et apprentissage des langues dans une pédagogie de la créativité ». Affects et acquisition des langues. Le langage et l’homme. L(2), 95-114.

Crommelinck, M. et Lebrun, J.-P. 2017. Un cerveau pensant : entre plasticité et stabilité. Toulouse : Eres

Damasio, A. 1995. L’erreur de Descartes – La raison des émotions. Paris : Odile Jacob.

Damasio, A. 2017. L’ordre étrange des choses. Paris : Odile Jacob.

Dewaele, J.-M. 2010. Emotions in Multiple Languages. Basingstole / Palgrave / Mac Millan.

Lison, C. 2018. « Quand j’innove, qu’est-ce-que cela donne réellement ? », Conférence plénière au colloque de Lausanne Innovation et pédagogie 15-16 février 2018.

Lubart, T. 2015. Psychologie de la créativité (2 ed.). Paris : Colin.

Pairon, J. 2018. « Perception des émotions et élaboration des cultures ». Communication présentée à la 8^e édition de la conférence internationale Intercultural pragmatics & Communication, Chypre, 8-10 juin 2018.

Pavlenko, A. 2014. The Bilingual Mind And What It Tells Us about Language and Thought. Cambridge : Cambridge University Press.

Plantin, C. 2011. Les bonnes raisons des émotions. Principes et méthode pour l’étude du discours émotionné. Berne : Peter Lang.

Sander, D. 2015. Le monde des émotions. Paris : Belin.

Comité scientifique

Les members du groupe ECLE (Emotion and Creativity in Language Education) de l’AILA (International Association of Applied Linguistics)

Fabienne Baider, Université de Chypre

Françoise Berdal-Masuy, Université de Louvain

Marion Botella, Université Paris Descartes

Isabelle Capron Puozzo, Haute école pédagogique du canton de Vaud

Cristelle Cavalla, Université Sorbonne Nouvelle

Simon Coffey, King’s college London

Laurence Mettewie, Université de Namur

Jacqueline Pairon, Université de Louvain

Christian Plantin, Université de Lyon

Back

Top

JOURNAL ON DATA SEMANTICS
SPECIAL ISSUE: BIG DATA SEMANTICS
Call for papers
The complexity of Big Data applications in conjunction with the lack of standards for representing their components, computations, and processes, have made the design of data-intensive applications a failure prone and resource-intensive activity. One of the reasons behind it can be identified in a lack of sound modeling practices. Indeed, multiple components and procedures must be coordinated to ensure a high level of data quality and accessibility for the application layers, e.g. data analytics and reporting. We believe that a major challenges of Big Data research requires - even more than developing new analytics - devising innovative data management techniques capable to deliver functional and non-functional properties like among others: data quality, data integration, metadata discovery, reconciliation and augmentation, model compliance, or regulatory compliance.
Data Semantics research can address such challenges in future research according to the FAIR principles, for implementing design procedures that generate Findable, Accessible, Interoperable, and Reusable data. Methods, principles, and perspectives developed by the Data Semantics community can significantly contribute to this goal. Solutions for integrating and querying schema-less data, for example, have received much attention. Standards for metadata management have been proposed to improve data integration among silos and to make data more discoverable and accessible through heterogeneous infrastructures. A further level of application of Data Semantics principles into Big Data technologies involves Representing Processes, i.e. representing the entire pipeline of technologies connected to achieve a specific solution and make this representation shareable and verifiable to support a mature implementation of the Big Data production cycle. This special issue of the Journal on Data Semantics aims at sharing research and practical achievements in the field of Big Data integration, storage, and processing. Topics of interest for submission include, but are not limited to:
? Big Data Management
? Metadata Management
? Big Data Persistence and Preservation
? Big Data Quality and Provenance Control
? Big Data Storage and Retrieval
? Big Data Integration Architectures and Techniques
? Data Source Discovery
? Big Data Profiling and Semantics Discovery
? Querying Heterogeneous Big Data Repositories
? Caching and Materializing Query Results
? Quality of Big Data Services
? Big Data Service Performance Evaluation
? Big Data Service Reliability and Availability
? Reproducibility of Big Data Services
? Verifiability of Big Data Services
? Assurance in Big Data Services
? Big Data Visualization
? Real Time Visualisation
? Visualization Analytics for Big Data
? Big Social Media Mining
? Big Data Security and Privacy
? Big Data System Security and Integrity
? Big Data Information Security
? Privacy-Preserving Big Data Analytics
? Usable Security and Privacy for Big Data
? Performance of Big Data Architectures
? Query Optimization
? Optimal Selection of Analytics
? Physical Structures

Guest Editors
Paolo Ceravolo, Università degli Studi di Milano, Italy
Robert Wrembel, Poznan University of Technology, Poland
Sylvio Barbon Junior, State University of Londrina, Brazil

Editorial Board
Antonia Azzini, T2C, Italy
Clodis Boscarioli, State University of West Paraná - UNIOESTE, Brazil Fadila Bentayeb, Université Lyon 2, France
Omar Boussaid, Université Lyon 2, France
Philippe Cudre-Mauroux, University of Fribourg, Switzerland
Jerome Darmont, Université Lyon 2, France
Luke Immes, University of Massachusetts Lowell, USA
Maurice van Keulen, University of Twente, The Netherlands Mariangela Lazoi, University of Salento, Italy
Marcello Leida, StrabioDB, Spain
M. Teresa Gómez López, University of Seville, Spain
Azzam Mourad, Lebanese American University of Beirut, Lebanon
Jaroslav Pokorny, Charles University, Czech Republic
Kai-Uwe Sattler, TU Ilmenau, Germany
Darja Solodovnikova, University of Latvia, Latvia
Sean Wolfgand Matsui Siqueira, Federal University of Rio de Janeiro State, Brazil Fadi Zaraket, American University of Beirut, Lebanon
Bruno Bogaz Zarpelão, State University of Londrina, Brazil

Timetable:
20 May 2019 - paper submission
10 July 2019 - author notification
31 August 2019 - revision submission
31 October 2019 - final acceptance notification
10 December 2019 - camera-ready submission

Submission Guidelines
JoDS is looking for high-quality papers on any topic relevant to the journal, including regular papers, survey papers, industry papers, short papers, position papers, and reports.
Submissions should contain original material that has not been submitted or published elsewhere. The submission should include an abstract and keywords, authors, and specify which author serves as contact author.All submissions will be carefully reviewed by at least three experts. Submissions have to be formatted according to the journal?s guidelines at http://www.springer.com/13740
and have to be uploaded into Springer?s Electronic Management System at https://www.editorialmanager.com/jods
JoDS is abstracted/indexed in: Google Scholar, DBLP, OCLC, Summon by ProQuest. Selected sample articles are available at http://www.springer.com/13740
ISSN: 1861-2032 (print version) ISSN: 1861-2040 (electronic version)

Any questions should be addressed to the Guest Editors
Paolo Ceravolo, paolo.ceravolo@unimi.it
Robert Wrembel, robert.wrembel@cs.put.poznan.pl
Sylvio Barbon Junior, barbon@uel.br

Back

Top

IEEE JSTSP Special Issue on
Automatic Assessment of Health Disorders Based on
Voice, Speech and Language Processing

The main aim of this special issue is to offer a forum that facilitates professional exchange of knowledge related to signal processing and machine learning methods for the assessment of a variety of health disorders related to voice and speech, and presentation of the recent research advances in the field. The scope of this special issue covers many aspects of voice and speech modelling and analysis, ranging from fundamental research to all kinds of advanced technologies and biomedical applications.

The scope of acceptable topics includes but is not limited to:

• Automatic detection of voice disorders from speech, electroglottographic signals and other associated sequences (e.g., air flow measurements, electromyographic signals, etc.)  
• Signal processing techniques to extract new biomarkers from speech and the associated signals
• Automatic assessment and classification of voice quality by machine learning approaches
• New strategies for parameterization and modelling of normal and pathological voices (e.g., biomechanical-based parameters, complexity modelling, etc)
• Speech enhancement for pathological and oesophageal speech
• Technical aids and hands-free devices: vocal prostheses and aids for the disabled
• Assessment of voice quality in rehabilitation
• Non-speech vocal emissions (e.g., infant cry, snoring)
• Multi-modal analysis of disordered voice and speech
• Automatic assessment and differential evaluation of neurological disorders (e.g., Alzheimer?s, Parkinson, epilepsy, autism, schizophrenia) from voice and speech
• Detection and evaluation of depression, stress, mood and risk of suicide from speech and associated signals   
• Processing and analysis of elderly speech and early detection of dementia
• Interaction of speech disorders with hearing impairments
• Computer-based diagnostic and training systems for voice and speech dysfunctions
• e-health and m-health applications  
• Child speech in typical and atypical language acquisition

This special issue aims at offering an interdisciplinary platform for presenting new knowledge in the assessment of voice and health disorders from speech. The emphases are on both basic and applied research related to the monitoring of voice and speech production status, as well as clinical evaluation of new developments.

In addition to topic-specific research results, we invite high-quality submissions of tutorial or overview nature. We also welcome creative papers outside the areas listed above but related to the overall scope of the special issue. Prospective authors can contact the Guest Editors to ascertain interest on topics that are not listed above.

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

Back

Top

IEEE JSTSP Special Issue on

Compact Deep Neural Networks with
Industrial Applications

Artificial neural networks have been adopted for a broad range of tasks in areas like multimedia analysis and processing, media coding, data analytics, etc. Their recent success is based on the feasibility of processing much larger and complex deep neural networks (DNNs) than in the past, and the availability of large-scale training data sets. As a consequence, the large memory footprint of trained neural networks and the high computational complexity of performing inference cannot be neglected. Many applications require the deployment of a particular trained network instance, potentially to a larger number of devices, which may have limitations in terms of processing power and memory e.g., for mobile devices or Internet of Things (IoT) devices. For such applications, compact representations of neural networks are of increasing relevance.

This special issue aims to feature recent work related to techniques and applications of compact and efficient neural network representations. It is expected that these works will be of interest to both academic researchers and industrial practitioners, in the fields of machine learning, computer vision and pattern recognition, media data processing, as well as fields such as AI hardware design etc. In spite of active research in the area, there are still open questions to be clarified concerning, for example, how to train neural networks with optimal performance while achieving compact representations, and how to achieve representations that do not only allow for compact transmission, but also for efficient inference.  This special issue therefore solicits original and innovative works to address these open questions in, but not limited to, following topics:

• Sparsification, binarization, quantization, pruning, thresholding and coding of neural networks
• Efficient computation and acceleration of deep convolutional neural networks
• Deep neural network computation for low power consumption applications
• Exchange formats and industrial standardization of compact & efficient neural networks
• Applications e.g. video & media compression methods using compressed DNNs
• Performance evaluation and benchmarking of compressed DNNs

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

Guest Editors Diana Marculescu, Carnegie Mellon University, USA Lixin Fan, JD.COM, Silicon Valley Labs, USA (Lead GE) Werner Bailer, Joanneum Research, Austria Yurong Chen, Intel Labs China, China

Back

Top

ACM Transactions on Internet Technology (TOIT)

Special Section on Computational Modeling and Understanding of Emotions in Conflictual Social Interactions 

Call for Papers: https://toit.acm.org/pdf/ACM-ToIT-CfP-ECSI-ext.pdf

Paper Submission Deadline: 31st March 2019

Author Guidelines and Templates: https://toit.acm.org/authors.cfm 

Paper Submission Website: https://mc.manuscriptcentral.com/toit 

The expression of social, cultural and political opinions in social media often features a strong affective component, especially when it occurs in highly-polarized contexts (e.g., in discussions on political elections, migrants, civil rights, and so on). In particular, hate speech is recognized as an extreme, yet typical, expression of opinion, and it is increasingly intertwined with the spread of defamatory, false stories. Current approaches for monitoring and circumscribing the spread of these phenomena mostly rely on simple affective models that do not account for emotions as complex cognitive, social and cultural constructs behind linguistic behavior. 

In particular, moral emotions possess a potential for advancing sentiment analysis in social media, especially since they provide insights on the motivations behind hate speech. Understanding these affective dynamics is important also for modelling human behavior in social settings that involve other people and artificial agents, as well as for designing socially-aware artificial systems.

How can we include finer grained accounts of emotions in computational models of interpersonal and social interactions, with the goal of monitoring and dealing with conflicts in social media and agent interactions? How can we leverage the recent advances in machine learning and reasoning techniques to design more effective computational models of interpersonal and social conflict? We invite contributions that address the foregoing questions by presenting enhanced computational models and processing methods.

INDICATIVE TOPICS OF INTEREST 

Computational models of emotions 

Moral emotions (e.g. contempt, anger and disgust) in conflictual social interactions

Affective dynamics in human-human and human-agent conflictual interactions 

Interplay of emotions in conflictual interactions

Dimensional and categorical emotion models in conflict representation

Automatic processing of affect in polarized debates on social media

Stance and hate speech detection

Affect in online virality and fake news detection

Opinions and arguments on highly controversial topics

Linguistic and multimodal corpora for affect analysis in conflictual interactions

Figurative and rhetorical devices in social contrasts

Applications

Conflict detection and hate speech monitoring in political debates

Conflict-aware and conflict-oriented conversational agents

Integration of social cues in human-agent interaction strategies 

Conflict-aware agents in pedagogical and coaching applications 

SUBMISSION FORMAT AND GUIDELINES

Author guidelines for preparation of manuscript and submission instructions can be found at: https://toit.acm.org/authors.cfm 

Please select ?Computational Modeling and Understanding of Emotions in Conflictual Social Interactions? under Manuscript Type dropdown in the Manuscript Central website.

Submission: 31 Mar 2019

First decision: 1 July 2019

Revision: 15 Aug 2019

Final decision: 1 Oct  2019

Final manuscript:  1 Nov  2019

Publication date: 1 Mar  2020

SPECIAL SECTION EDITORS

Chloé Clavel, Institut-Mines-Telecom, Telecom-ParisTech, LTCI,  France

http://clavel.wp.mines-telecom.fr

Rossana Damiano, Università degli Studi di Torino, Italy

http://www.di.unito.it/~rossana/

Viviana Patti, Università degli Studi di Torino, Italy

http://www.di.unito.it/~patti

Paolo Rosso, Universitat Politècnica de València, Spain

http://users.dsic.upv.es/~prosso

ACM TOIT Editor-in-Chief

Ling Liu, Department of Computer Science, Georgia Institute of Technology

CONTACT

Please send any queries about this CfP to ecsi.toit@gmail.com.

Back

Top

Special Issue on Speech & Dementia,

Computer Speech and Language.

The CfP is online here:
https://www.journals.elsevier.com/computer-speech-and-language/call-for-papers/special-issue-on-speech-dementia

Organizers:

Heidi Christensen (University of Sheffield, GBR),

Frank Rudzicz (University of Toronto, CAN),

Johannes Schröder (University Heidelberg, DEU)

Tanja Schultz (University of Bremen, CDEU)

Back

Top

Call for papers – TIPA journal vol. 36, 2020

Back

Top