ISCApad #247 |
Friday, January 18, 2019 by Chris Wellekens |
7-1 | Special issue of JSTSP on Far-Field Speech Processing in the Era of Deep Learning Speech enhancement, Separation and RecognitionSpecial Issue onFar-Field Speech Processing in the Era of Deep Learning
|
Top |
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.
|
|
|
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.
Top |
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:
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.
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).
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 8e 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
Top |
Top |
Auditory Displays and Auditory User Interfaces
Art-Design-Science-Research
Guest Editors:
Myounghoon Jeon, Virginia Tech, USA (myounghoonjeon@vt.edu)
Areti Andreopoulou, University of Athens, Greece (a.andreopoulou@music.uoa.gr)
Brian FG Katz, Sorbonne University, France (brian.katz@sorbonne-universite.fr)
Deadline for paper submission: May 1, 2019
This special issue concerning Auditory Displays and Auditory User Interfaces: Art-Design-Science-Research (ADSR) is motivated by the theme of the 2018 Conference of ICAD (International Community for Auditory Display), a wordplay on the term ?ADSR? (Attack-Decay-Sustain-Release), commonly used in sound-related domains. This is an open call to authors for contributions under this broad theme. We welcome technical, theoretical, and empirical papers that can contribute to any aspect (art, design, science, and research) of auditory displays and auditory user interfaces.
Designers and researchers have tried to make auditory displays and auditory user interfaces more useful in numerous areas, extending typical visuo-centric interactions to multimodal and multisensorial systems. Application areas include education, assistive technologies, auditory wayfinding, auditory graphs, speech interfaces, virtual and augmented reality environments, and associated perceptual, cognitive, technical, and technological research and development. Research through design or embedded design research has recently become more pervasive for auditory display designers. Hence, we welcome all types of ?design? activities as a necessary process in auditory display. In addition, methodical evaluation and analysis have become more prominent, leading to more robust science. In this iterative process, auditory displays can achieve improved reliability through robust and repeatable research. In some areas, we have already arrived at the sciencestage, while in other areas we are still exploring the possibilities.
Pursuing novelty encourages artists to seek the integration of different genres and transform modalities. By definition, auditory displays and sonification transform data into sound. Thanks to the characteristics of this transformation, there have been active interactions between auditory displays and various forms of art. Hence, we would also like to invite contributions addressing artistic approaches to auditory displays and auditory user interfaces.
Rather than insisting on a specific approach, we encourage a broad spectrum of diverse strategies. In other words, all these approaches ? art, design, science, and research ? should be balanced and utilized more flexibly depending on the circumstances.
Topics of interest for this special issue include, but are not limited to, the following:
Schedule:
Submission deadline: May 1, 2019
1st round review: August 1, 2019
2nd round review: October 1, 2019
Publication: Spring 2020
Authors Instructions:
Submissions should be 8-12 pages long, presenting original unpublished work. Previously presented conference and workshop papers should include a minimum of 30% new content. The authors will be required to follow the Author?s Guide for manuscript submission to the Journal of Multimodal User Interfaces published by Springer.
(http://www.springer.com/computer/hci/journal/12193)
During the submission process, please select ?S.I.: Auditory Display 2018? as article type.
************************************************
Myounghoon 'Philart' Jeon, Ph.D.
Associate Professor
Grado Department of Industrial and Systems Engineering
Virginia Tech
519D Whittemore Hall
1185 Perry St. Blacksburg, VA 24061
myounghoonjeon@vt.edu
Top |
Organisation spatiale et temporelle des pauses en parole et en discours
http://www.revues.armand-colin.com/lettres-langues/langages/langages-ndeg-211-32018
Sommaire du numéro
Pages : 5-12 |
L?organisation spatiale et temporelle de la pause en parole et en discours |
Christelle Dodane |
|
Pages : 13-40 |
Variation de la durée des pauses silencieuses : Impact de la syntaxe, du style de parole et des disfluences |
Iulia Grosman |
|
Pages : 41-59 |
Hésitations et faux-départs dans le langage adulte et enfantin : Le rôle de la prosodie |
Ester Scarpa |
|
Pages : 61-80 |
Le rôle de la pause dans l?acquisition de la première syntaxe en français |
Christelle Dodane |
|
Pages : 81-95 |
Détails phonétiques dans la réalisation des pauses en Français : Etude de parole lue en langue maternelle vs en langue étrangère |
Camille Fauth |
|
Pages : 97-109 |
Que révèle la pause silencieuse sur l?accessibilité cognitive d?un référent et le vieillissement langagier ? |
Lucie Rousier-Vercruyssen |
|
Pages : 111-125 |
Que cachent les pauses silencieuses en parole ? Une étude de cas |
Fabrice Hirsch |
|
Pages : 127-141 |
Quand la pause devient-elle un symptôme du bégaiement ? Une étude acoustique et articulatoire |
Ivana Didirková |
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
Top |