(2017-08-14) Course: Machine Learning Applied to Bioinformatics and Speech Technology, Univ. Joensuu, Finland
UEF SUMMER SCHOOL 2017 Joensuu, Finland http://summerschool.uef.fi/ August 14-25, 2017 ***** Registration deadline: May 26, 2017 ***** -o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o-o Course: Machine Learning Applied to Bioinformatics and Speech Technology http://www.uef.fi/en/web/summerschool/machine-learning-applied-to-bioinformatics-and-speech-technology Course has two options: * Lectures + learning diary (August 14 - 18), total 2 ECTS * Lectures + learning diary + individual project (August 14 - 25), total 5 ECTS Teaching language: English Level: Doctoral, Master University of Eastern Finland (UEF) hosts a number of different summer courses in August 2017. The course on Machine Learning Applied to Bioinformatics and Speech Technology is co-organized by the School of Computing (Speech track) and Institute of Biomedicine (Bioinformatics track). Contact teaching takes place from August 14th to 18th. Individual optional project work is from August 21th to 25th. Contents The first two days include a general introduction to machine learning including topics such as deep learning, Bayesian graphical models and modeling sequential data. Course is intended to be self-contained with no prior knowledge of machine learning required. After the introductory part, the participants will choose one of the alternative course tracks (speech technology or bioinformatics). The lectures are delivered physically in two different locations of the UEF campuses, Joensuu and Kuopio (150 km apart). But it is possible to attend the lectures of either course from both campuses remotely through a video connection provided by UEF. The speech processing teaching takes place in Joensuu and bioinformatics teaching in Kuopio. In the speech/audio track we focus on state-of-the-art automatic speaker verification (ASV) and spoken language identication (LID) technology. In addition to introducing the basic models and software tools for session/channel compensation to increase robustness (e.g. factor analysis and i-vectors), the topics include also audio forensics and speech anti-spoofing (or presentation attack detection) techniques, including the ASVspoof challenge series. Using these techniques system would be able to know whether recorded audio was tampered somehow or that the spoken by a human or produced by a machine. Open-source software tools will also be introduced. The speech track is recommended especially for PhD students (and MSc students close to graduation) who might be already familiar with the basics of speech processing and interested in obtaining a quick overview of both basic principles, state-of-the-art techniques and selected emerging trends in speaker and language recognition. Speech processing confirmed lecturers: Cemal Hanilci, Bursa Technical University, Turkey Ville Hautamäki, University of Eastern Finland (organizer) Tomi Kinnunen, University of Eastern Finland (organizer) Kong Aik Lee, Institute for Infocomm Research, Singapore Modes of study: Lectures (4 days), hands on practicals (1 day), project work (1 week) and learning diary Social program: We will also organise some guided social programme in the evenings and during the weekend. This will include a welcome dinner, a guided city tour by bus, sauna evening, a one-day trip to Koli national park during the weekend etc. The activities will mostly be included in your course fee, but some of them may have a small participation fee. Assessment: pass/fail. Students who pass will receive certificate. Registration: http://www.uef.fi/en/web/summerschool/how-to-apply Registration fee: 500 EUR Accommodation: http://www.uef.fi/en/web/summerschool/accommodation More information: villeh@cs.uef.fi and tkinnu@cs.uef.fi
(2017-08-15 )CfP SigDial 2017 Special Session: Natural Language Generation for Dialogue Systems, Saarbrüken, Germany
=====================================
SigDial 2017 Special Session:
Natural Language Generation for Dialogue Systems
First Call for Papers
Paper Submission: 18th April 2017
http://www.sigdial.org/workshops/conference18/
=====================================
* MOTIVATION
While natural language generation (NLG) for dialogue interaction has been a long-standing research topic, there has been a recent explosion of work due to industrial interest in conversational assistants such as Alexa, Siri, Cortana and Google Assistant. Recent advances in the field of deep learning together with the availability of large corpora of human dialogues from social media has also contributed to new research techniques for language generation. However, to date, neural methods have not been able to replicate much of the rich dialogue phenomena targeted by previous rule-based, statistical and data-driven approaches for language generation for dialogue.
* TOPIC SUBMISSION
We invite submissions which address specific issues including but not limited to:
- Generation in the context of a dialogue with appropriate use of anaphoric forms, such as pronouns and ellipses;
- Generation of turns where information is structured using rhetorical relations, as in the case of recommendations or other persuasive genres;
- Selection and organization of content in a dialogue turn;
- Sentence planning and lexical choice for dialogue interaction;
- Evaluation of language generation for dialogue systems;
- Corpus-based analyses of human-human dialogue to inform NLG for dialogue systems;
- Critical comparison between capabilities of different kinds of models.
- Providing and investigating new resources, such as data sets and tools.
- We also welcome submissions which make use of the new E2E NLG challenge data set (http://www.macs.hw.ac.uk/InteractionLab/E2E/).
* SUBMISSION FORMAT
Long paper submissions will follow the SigDial 2017 format and will be part of the general conference submission and review system. They will be treated as regular SIGDIAL papers and become archival.
- Long papers must be no longer than eight pages + unlimited pages for references + 2 additional pages for appendix (linguistic examples, algorithms etc.)
- Short position papers (2 pages + unlimited pages for references) with a single point to make, e.g. a proposal for a shared task for NLG for dialogue. These will be presented as short talks or posters, and the papers will be added to the web page for the special session (TBA), but will not count as an archival publication.
* IMPORTANT DATES
We will follow the SigDial 2017 schedule, and papers should be submitted using the SIGDIAL conference submission site. http://www.sigdial.org/workshops/conference18/
Paper Submission Deadline: Tuesday, 18 April 2017 (23:59, GMT-11)
Paper Notification: Friday, 9 June 2017
Final Paper Submission: Friday, 7 July 2017
Conference: Tuesday, 15 August 2017 to Thursday, 17 August 2017
* CONTACT
Marilyn Walker
* ORGANISING COMMITTEE
Marilyn Walker, University of California Santa Cruz (Chair)
Verena Rieser, Heriot-Watt University
Vera Demberg, Universität des Saarlandes
Dietrich Klakow, Universität des Saarlandes
Dilek Hakkani-Tur, Google Research
David M. Howcroft, Universität des Saarlandes
Shereen Oraby, University of California Santa Cruz
PACLING 2017 will be a high-quality, workshop-style conference whose aim is to promote friendly scientific interaction relating to computational linguistics among Pacific Rim countries. The emphasis of the conference is on interdisciplinary scientific exchange demonstrating openness towards original high-quality research including one which might fall outside current dominant schools of thought, and on technological transfer within and across the Pacific region. The conference represents a unique forum for scientific and technological exchange, being smaller than ACL and COLING, and more regional with extensive representation from the Pacific. TOPICS
Substantial, original, and unpublished research is welcome on any topics in computational linguistics, including, but not limited to the following:
Phonology and Phonetics
Morphology and Morphological Analysis
Syntax and Syntactic Analysis
Semantics and Semantic Analysis
Pragmatics and Discourse Analysis
Spoken Language and Dialogue
Language Resources
Corpora and Corpus-based Language Processing
Text and Message Understanding
Text and Message Generation
Information Extraction and Text Mining
Information Retrieval and Question-Answering
Text Summarization
Language Learning
Machine Translation
Natural Language Interfaces
Semantic Web and Semantic Computation
IMPORTANT DATES
Submission deadline: April 19, 2017 Notification of acceptance: May 25, 2017 Camera-ready copy due: July 10, 2017 Conference dates: August 16 - 18, 2017
SUBMISSION OF PAPERS Authors should prepare submissions in English of up to 6 pages including references. Guidelines and style sheets (based on the IEEE format) are available here:
Papers that are being submitted to other conferences, whether verbatim or in essence must declare this fact. If a paper appears at another conference, it must be withdrawn from PACLING 2017. Papers that violate these requirements are subject to rejection without review.
The submitted papers need not be anonymous.
All papers will be submitted electronically in PDF format, through the web-based conference management system called EasyChair. To submit through EasyChair, go to the PACLING 2017 EasyChair page: https://www.easychair.org/conferences/?conf=pacling2017
Login using your existing EasyChair account, or create a new account following the instructions on the site. Once you have logged in, click on the 'New Submission' link located in the top-left corner of the menu bar, and then follow the instructions to submit your paper.
BEST PAPER AWARD AND BEST STUDENT PAPER AWARD Awards for best paper and best student paper will be selected based on the reviews by the program committee.
PUBLICATION All accepted papers will be published in the conference proceedings in CD-ROM and made available on the website (after a given date).
ORGANIZATION
Program Chair: Koiti Hasida, Professor, Social ICT Research Center University of Tokyo
(2017-08-20) CfP INTERSPEECH 2017 Special session on 'Incremental Processing and Responsive Behaviour'
Call for Paper INTERSPEECH 2017 Special session on Incremental Processing and Responsive Behaviour ======================================================================================
Incremental processing ? i. e., the online, and ideally real-time processing of streams of information about an ongoing event, as it happens ? has become a highly relevant research area. Is is particularly true for speech, which is an inherently sequential medium, and in interactive situations, where responsivity is key. Incremental processing techniques are used across speech recognition and synthesis, voice conversion, understanding, generation, syntax parsing, machine translation, and in applications such as dialogue systems, situated and multimodal interaction, robotics, or speech-to-speech translation.
The aspect of incrementality is largely orthogonal to the typical session/topic layout at Interspeech and hence work on incremental processing is usually spread over a multitude of sessions at Interspeech (and related conferences), which leads to a fragmentation of expertise and discussions. Our special session sets out to unite the spread-out field in order to provide a venue for joint discussion of incrementality itself rather than having to focus on the individual problems tackled.
We are inviting researchers interested in incrementality in all its aspects such as: · solving specific problems of automatic speech and language processing in an incremental fashion · methodology and theory of incremental processing including its evaluation · psycholingiustic findings and interaction of modalities · predictive/reactive frameworks and the integration of incrementality into systems · researching the influence on interactions in end-to-end systems (as well as human-human interaction) · reactive/human-centered machine learning · reactive behaviour based on partial understanding, and more.
The topic of our special session is to be connected with a follow-up special issue in Computer, Speech & Language.
We invite you to submit original papers on any of the research themes listed above. When submitting papers, please make sure that you select scientific area topic: [11.13] Special Session on ' Incremental Processing and Responsive Behaviour' in the INTERSPEECH 2017 submission system.
25 August 2017 KTH Royal Institute of Technology, Stockholm, Sweden
GLU 2017 aims at bringing together researchers working with modeling different aspects of grounding language acquisition and understanding.
Although speech and language technology have reached a level of maturity, machines still fall short of human performance, especially when considering flexibility and robustness. It is therefore desirable to extend the machine learning approach which has been applied to speech and language technology, and emulate more closely the way humans and living systems acquire language.
Almost all animals exploit vocal signals for a range of ecologically-motivated purposes: from detecting predators/prey and marking territory, to expressing emotions, establishing social relations and sharing information. Whether it?s a bird raising an alarm, a whale calling to potential partners, a dog responding to human commands, a parent reading a story with a child, or a businessperson accessing stock prices using Siri on an iPhone, vocalisation provides a valuable communications channel through which behaviour may be coordinated and controlled, and information may be distributed and acquired. Indeed, the ubiquity of vocal interaction has led to research across an extremely diverse array of fields, from assessing animal welfare, to understanding the precursors of human language, to developing voice-based human-machine interaction. Clearly, there is potential for cross-fertilisation between disciplines; for example, using robots to investigate contemporary theories of language grounding, using machine learning to analyse different habitats or adding vocal expressivity to the next generation of autonomous social agents. However, many opportunities remain unexplored, not least due to the lack of a suitable forum.
VIHAR-2017 aims to bring together researchers studying vocalisations and speech-based interaction in-and- between humans, animals and robots from a variety of different fields. The workshop is being organised by participants of a recent Dagstuhl Seminar on the same topic, and follows the publication of a short review article: http://journal.frontiersin.org/article/10.3389/frobt.2016.00061/full. VIHAR-2017 will provide a timely opportunity for scientists and engineers from different fields to share theoretical insights, best practices, tools and methodologies, and to identify common principles underpinning vocal behaviour in a multi-disciplinary environment.
We invite original submissions of four-page INTERSPEECH-style papers (plus one page of references) or two-page extended abstracts (including references) in all areas of vocal interactivity. Suggested workshop topics may include, but are not limited to, the following areas: * physiological and morphological similarities/differences between vocal systems in animals * properties and functions of animal signals * evolution of vocal interactivity * vocal imitation and learning * conveyance of emotion * comparative analyses of human and animal vocalisations * use of vocalisation * vocal interactivity between non-conspecifics * spoken language systems * technology-based research methods
Key Dates: Submission deadline - 2 June 2017 Notification of acceptance - 30 June 2017 Workshop - 25-26 August 2017
Organisers: Robert Eklund, Linköping University Angela Dassow, Carthage College Ricard Marxer, University of Sheffield Roger K. Moore, University of Sheffield Bhiksha Raj, Carnegie Mellon University Rita Singh, Carnegie Mellon University Serge Thill, University of Skövde Benjamin Weiss, Technical University of Berlin
If you wish to join the VIHAR community, please subscribe to our mailing list by entering your e-mail address at http://www.freelists.org/list/vihar and then responding to the confirmation e-mail that you will receive from the list server.
AVSP is a uniquely interdisciplinary conference, focusing on the effects of auditory and visual speech information on human perception, machine recognition, and human-machine interaction. AVSP conferences attract many researchers from various fields, such as psychology, computer engineering, neuroscience, linguistics, and robotic engineering. AVSP 2017 is a satellite workshop of INTERSPEECH 2017, one of the largest conferences on speech communication.
The AVSP conference will be held in Stockholm, Sweden, August 25 & 26, 2017.
CONFERENCE TOPICS
Submission of papers are invited in all areas of auditory-visual speech processing and facial animation and including but not limited to:
- Human recognition of audio-visual speech
- Machine recognition of audio-visual speech
- Human and machine models of multimodal integration
- Multimodal processing of spoken events
- Cross-linguistic studies
- Developmental studies
- Role of gestures accompanying speech
- Modeling, synthesis and recognition of facial gestures
- Audio-visual speech synthesis
- Audio-visual prosody
- Emotion and Expressivity modeling
- Neuropsychology and neurophysiology of audio-visual speech processing
- Scene analysis using audio and visual speech information
INVITED SPEAKER
Sonja A Kotz
Professor and Chair in Neuropsychology and Translational Cognitive Neuroscience
(2017-08-25) CfP First International Workshop on Grounding Language Understanding (GLU 2017), Stockholm, Sweden
Call for papers GLU 2017 ==================== First International Workshop on Grounding Language Understanding (GLU 2017)
ISCA Satellite Workshop of Interspeech 2017 Stockholm University, August 25th 2017
Important Dates ============= Paper Submission: **Wednesday, 31 May 2017** Paper Notification Acceptance: **Wednesday, 28 June 2017** Publication of Full Programme: **Wednesday, 12 July 2017** Camera-ready Paper Due: **Wednesday, 26 July 2017** Registration Deadline: **Wednesday, 2 August 2017** Workshop: **Friday, 25 August 2017**
The purpose of this workshop is to bring together researchers from different disciplines (linguistics, language, robotics, systems neuroscience, cognitive science, signal processing, etc.) working with modeling different aspects of grounding language acquisition and understanding. Although speech and language technology have reached a level of maturity, machines still fall short of human performance, especially when considering flexibility and robustness. It is therefore desirable to extend the machine learning approach which has been applied to speech and language technology, and emulate more closely the way humans and living systems acquire language. Desirable properties of the new learning approaches would include: * being less dependent on annotated data, * acquiring knowledge from multimodal inputs (acoustic, visual, tactile), * learning from interaction, * relating learning to the situational context, * grounding language in the perceptual, emotional and sensorimotor experience of the agent This requires a highly multidisciplinary approach, combining the field of human language processing, speech technology, machine learning, developmental robotics and cognitive and systems neuroscience.
Confirmed keynote speakers: ======================== * Emmanuel Dupoux, École des Hautes Etudes en Sciences Sociales, Paris, France. * Katerina Pastra, Cognitive Systems Research Institute, Athens, Greece * Robert Legenstein, Graz University of Technology, Austria
Scientific Area Topics ================= * Language Learning via Grounded Dialogue * Language Generation for Embodied Tasks * Grounded Knowledge Representations * Skill Learning via Interactive Dialogue * Aligning and Translating Language to Situated Actions * Instructions for Navigation/Articulation/Manipulation * Mapping Language and World * Grounded Reinforcement Learning * Language-based Game Playing for Grounding * Structured and Deep Learning Models for Embodied Language * New Datasets for Embodied Language * Better Evaluation Metrics for Embodied Language
Submission and Format =================== We invite original submissions from 3 pages including references to 4 pages of text, plus one page (maximum) for references in the INTERSPEECH format. Each submission will be reviewed by at least two members of the Scientific Review Committee.
Proceedings and Publication ======================= Accepted papers will be published in the open access GLU2017 (indexed) proceedings.
Registration ========== We are trying to keep the costs as low as possible. Registration fees should be around 150?. These will include the lunch, coffee breaks and the evening dinner on the day of the workshop.
Sponsors ======== GLU2017 is supported by the CHIST-ERA/IGLU consortium and is an ISCA sponsored event and a satellite event for Interspeech 2017 in Stockholm.
(2017-08-27) CfP 20th International Conference on TEXT, SPEECH and DIALOGUE (TSD 2017), Praha (Prague), Czech Republic
TSD 2017 - PRELIMINARY CALL FOR PAPERS **************************************************************************
The twentieth anniversary International Conference on TEXT, SPEECH and DIALOGUE (TSD 2017) Praha (Prague), Czech Republic August 27-31, 2017 http://www.tsdconference.org
TSD HIGHLIGHTS
* Invited speakers: Tomas Mikolov and other eminent personages with various expertise covering speech modeling, acoustic-phonetic decoding, dialogue systems, and semantics have been asked to give their respective pieces of speech. * TSD is traditionally published by Springer-Verlag and regularly listed in all major citation databases: Thomson Reuters Conference Proceedings Citation Index, DBLP, SCOPUS, EI, INSPEC, COMPENDEX, etc. * TSD offers high-standard transparent review process - double blind, final reviewers discussion. * TSD will take place in the historical centre of Prague, the Capital of the Czech Republic in co-operation with the Institute of Formal and Applied Linguistics, Faculty of Mathematics and Physics of the Charles University. * TSD provides an all-service package (conference access and material, all meals, one social event, etc.) for an easily affordable fee starting at 290 EUR for students and 360 EUR for full participants.
TSD SERIES
TSD series have evolved as a prime forum for interaction between researchers in both spoken and written language processing from all over the world. Proceedings of the TSD conference form a book published by Springer-Verlag in their Lecture Notes in Artificial Intelligence (LNAI) series. The TSD proceedings are regularly indexed by Thomson Reuters Conference Proceedings Citation Index. LNAI series are listed in all major citation databases such as DBLP, SCOPUS, EI, INSPEC, or COMPENDEX.
TOPICS
Topics of the 20th anniversary conference will include (but are not limited to):
Speech Recognition (multilingual, continuous, emotional speech, handicapped speaker, out-of-vocabulary words, alternative way of feature extraction, new models for acoustic and language modelling).
Corpora and Language Resources (monolingual, multilingual, text, and spoken corpora, large web corpora, disambiguation, specialized lexicons, dictionaries).
Speech and Spoken Language Generation (multilingual, high fidelity speech synthesis, computer singing).
Tagging, Classification and Parsing of Text and Speech (multilingual processing, sentiment analysis, credibility analysis, automatic text labeling, summarization, authorship attribution).
Semantic Processing of Text and Speech (information extraction, information retrieval, data mining, semantic web, knowledge representation, inference, ontologies, sense disambiguation, plagiarism detection).
Integrating Applications of Text and Speech Processing (machine translation, natural language understanding, question-answering strategies, assistive technologies).
Automatic Dialogue Systems (self-learning, multilingual, question-answering systems, dialogue strategies, prosody in dialogues).
Multimodal Techniques and Modelling (video processing, facial animation, visual speech synthesis, user modelling, emotion and personality modelling).
The official language of the event is English, however, papers on issues related to text and speech processing in languages other than English are strongly encouraged.
IMPORTANT DATES
March 31, 2017 ............ Deadline for submission of contributions May 10, 2017 .............. Notification of acceptance or rejection May 31, 2017 .............. Deadline for submission of camera-ready papers
August 27-31, 2017 ........ TSD2017 conference date
The proceedings will be provided on flash drives in form of navigable content. Printed books will be available for extra fee.
CONFERENCE FEES
The conference fee depends on the date of payment and on the participant's status (full or student). It includes one copy of the conference proceedings (on a USB flash drive), refreshments/coffee breaks, lunches and dinners, opening dinner, welcome party, mid-conference social event admissions, and organizing costs. In order to lower the fee as much as possible, the accommodation and the conference trip are not included in it this time.
Full participant: early registration by May 31, 2017 - CZK 10 000 (approx. 360 EUR) late registration by August 1, 2017 - CZK 11 000 (approx. 400 EUR) on-site registration - CZK 12 000 (approx. 444 EUR)
Student (reduced): early registration by May 31, 2017 - CZK 8 000 (approx. 290 EUR) late registration by August 1, 2017 - CZK 8 700 (approx. 322 EUR) on-site registration - CZK 10 000 (approx. 360 EUR)
Please, keep in mind that the fees are preliminary and they may slightly change in the future. We are also doing our best to find a way to reduce the fees for students.
LOCATION
Praha (Prague)--also called The City of a Hundred Spires or The Heart of Europe--is situated in the very centre of Bohemia on the banks of the river Vltava. There live more than 1.2 million people in the metropolitan area. Thus, Praha is considered the centre of science, higher education, culture, economy and authorities.
The city is divided into ten districts. Each of them offers its own charming atmosphere predicated upon its rich history. A good example can be the Jewish Quarter (Josefov) known especially for the legend of Golem and famous writer Franz Kafka. Then, walking the Parizska street (said to be the most luxurious street in the city), there is the Old Town Square. One of the most important squares of the city renowned for the rare Prague Astronomical Clock (Orloj), number of galleries, Bethlehem Chapel and a monument of religious reformer Jan Hus.
The next place of interest can be found in the area of the New Town. The Wenceslas square with the monument of St. Wenceslas, the patron saint of the Czech state, is the longest square of the republic. Its capacity is fully used by various shops, restaurants, clubs and street artists. Also the renaissance revival-styled building of National Museum, which is now under reconstruction, is situated on the upper end of the square.
Modern art and architecture together with technical mastery demonstration are represented by the Zizkov Television Tower, the Dancing House (Fred and Ginger Building) or the Stefanik's Observatory on the Petrin hill located in the neighbourhood of the quarter Hradcany. Also Krizik's light fountain or Industrial Palace in the area of the Holesovice Showground are worth seeing.
However, the dominant feature of the skyline is still created by the Prague Castle and the Gothic St. Vitus Cathedral spires. The Golden Lane heading down to the Lesser Town shows the tiny and colorful medieval houses. There are many bridges connecting the banks of the Vltava River.
However, only one of them is well known in the whole world--the Charles bridge. Czech King and Holy Roman Emperor Charles IV promoted its construction in the 14th century. The bridge is 520 metres long and stands for a connection between the Lesser Town and the Old Town. It was built in the Gothic style as well as the St. Vitus Cathedral.
Charles IV was also the founder of the University, which now proudly bears his name--The Charles University. It is one the world's oldest universities and with 17 faculties, 3 institutes, 6 centres of teaching, research and development it is also the largest and best rated university in the Czech Republic. The students can choose some of the 642 courses within 300 of accredited degree programmes in the field of medicine, law, theology, pharmacy, arts, science, mathematics and physics, education, social sciences, physical education and sports, and humanities.
We are justifiably very proud of the fact that the campus of the Charles University is going to host the TSD2017 conference.
ABOUT CONFERENCE
The conference is organized by the Faculty of Applied Sciences, University of West Bohemia, Pilsen, the Faculty of Informatics, Masaryk University, Brno, and the Institute of Formal and Applied Linguistics, Faculty of Mathematics and Physics of the Charles University.
The TSD2017 organizing committee has again applied for TSD2017 to be recognized as an INTERSPEECH 2017 satellite event.
Venue: Faculty of Mathematics and Physics of the Charles University Mala Strana Campus - 'S' Building Malostranske nam. 2/25 CZ-118 00 Praha 1
Accommodation: Orea Hotel Pyramida **** Belohorska 24 CZ-169 00 Praha 6
CONTACT
The preferred way of contacting the conference organizing committee is writing an e-mail to: Mrs Romana Strapkova, TSD2017 Conference Secretary E-mail: tsd2017@tsdconference.org Phone: (+420) 736 664 500
All paper correspondence regarding the conference should be addressed to:
TSD2017 - KIV Fakulta aplikovanych ved Zapadoceska univerzita v Plzni Univerzitni 8 CZ-306 14 Plzen Czech Republic
Fax: (+420) 377 632 402 -- Please, mark the faxed material with large capitals 'TSD' on top.
EUSIPCO 2017 CALL FOR PAPERS KOS ISLAND, GREECE 28th AUGUST- 2nd SEPTEMBER 2017
The 25th European Signal Processing Conference (EUSIPCO 2017) will be held in the Greek island of Kos from August 28 to September 2, 2017, at the Kos International Convention Center. The flagship conference of the European Association for Signal Processing (EURASIP) will offer a comprehensive technical program addressing all the latest developments in research and technology for signal processing and its applications. It will feature world-class speakers, oral and poster sessions, keynotes and plenaries, exhibitions, demonstrations, tutorials and satellite workshops, and is expected to attract many leading researchers and industry figures from all over the world.
Technical scope: We invite the submission of original, unpublished technical papers on topics including but not limited to: - Audio and acoustic signal processing - Speech and language processing - Image and video processing - Multimedia signal processing - Signal processing theory and methods - Sensor array and multichannel signal processing - Signal processing for communications - Radar and sonar signal processing - Signal processing over graphs and networks - Nonlinear signal processing - Statistical signal processing - Compressed sensing and sparse modeling - Optimization methods - Machine learning - Bio-medical image and signal processing - Signal processing for computer vision and robotics - Information forensics and security - Signal processing for power systems - Signal processing for education - Bioinformatics and genomics - Signal processing for big data - Signal processing for the internet of things - Design and implementation of signal processing systems - Other signal processing areas
Accepted papers will be included in IEEE Xplore®. EURASIP Society enforces a ?no-show? policy. Procedures to submit papers, proposals for special sessions, tutorials and satellite workshops are detailed at the EUSIPCO website (www.eusipco2017.org).
** IMPORTANT DATES ** Special Session proposals: 30 December 2016 (closed) Satellite Workshop proposals: 20 February 2017 Tutorial proposals: 5 March 2017 Full paper submissions: 5 March 2017 Notification of paper acceptance: 25 May 2017 Camera-ready papers: 17 June 2017
STUDENT PAPER AWARDS: ?EUSIPCO Best Student Paper Awards? will be presented at the conference banquet. Papers will be selected by a committee composed of area and technical chairs.
PLACE: Kos has direct airport connections to many European cities and is located in the middle of the Dodecanese group of islands at the southeast part of the Aegean archipelagos. Rich in historic heritage, it has been a crossroad of many civilizations and was the birthplace of Hippocrates, the father of western medicine, and his ancient school of medicine. It offers a cosmopolitan mix of a vibrant city lifestyle, idyllic beaches, historic tours, easy access to other Greek islands and many other Mediterranean attractions.
TUTORIAL AND SPECIAL SESSION PROPOSALS: Tutorials will be held on August 28, 2017. Brief tutorial proposals should include title, outline, contact information, biography and selected publications for the presenter(s), and a description of the tutorial and material to be distributed to participants. Special session proposals should include title, rationale, session outline, contact information, and a list of invited papers.
SATELLIT? WORKSHOP PROPOSALS: The 2017 edition of EUSIPCO is proud to organize a full day of thematic workshops after the end of the main conference, which will provide a forum to participate in specific scientific events and present research focused on current innovative topics in signal processing technology and its extension to other fields.
3 MINUTE THESIS (3MT): EUSIPCO 2017 is offering a 3 Minutes Thesis contest, where PhD students have three minutes to present a compelling oration on their thesis and its significance. It is an exercise for students to consolidate their ideas so they can present them concisely to an audience specialized in different signal processing fields.
Please refer to the EUSIPCO 2017 website for additional information.
ORGANIZING COMMITTEE: GENERAL CHAIRS Petros Maragos, National Technical University of Athens, Greece Sergios Theodoridis, National Kapodistrian University of Athens, Greece
TECHNICAL PROGRAM CHAIRS Konstantinos Diamantaras, Alexander Tech. Educ. Inst. of Thessaloniki, Greece Stefanos Kollias, National Technical University of Athens, Greece Constantine Kotropoulos, Aristotle University of Thessaloniki, Greece Gerasimos Potamianos, University of Thessaly, Greece
PLENARY CHAIRS Nikos Sidiropoulos, University of Minnesota, USA Shri Narayanan, University of Southern California, USA
TUTORIAL CHAIRS Béatrice Pesquet-Popescu, Télécom ParisTech, France Aggelos Pikrakis, University of Piraeus, Greece
WORKSHOP CHAIRS Kostas Berberidis, University of Patras, Greece Iasonas Kokkinos, CentraleSupelec, France
FINANCE CHAIR Costas Tzafestas, National Technical University of Athens, Greece
PUBLICATION CHAIRS Petros Boufounos, Mitsubishi Electric Research Labs, USA Elias Manolakos, National Kapodistrian University of Athens, Greece
LOCAL ARRANGEMENTS CHAIR Giorgos Stamou, National Technical University of Athens, Greece
PUBLICITY CHAIR Panagiotis Tsakalides University of Crete, Greece
INTERNATIONAL LIAISONS North America: Georgios Giannakis, University of Minnesota, USA South America: Paulo Diniz, Universidade Federal do Rio de Janeiro, Brazil Asia: Hideaki Sakai, Kyoto University, Japan EuCNC: Luis M. Correia, IST-University of Lisbon, Portugal
We solicit proposals for half- or full-day workshops that will be held together with the European Signal Processing Conference (EUSIPCO) in Kos Island, Greece, from August 28 to September 2, 2017.
Workshops will take place on Saturday, September 2, 2017, at the same venue as the main conference, that is the Kos International Convention Center.
We welcome proposals on emerging topics that are not anticipated to be fully explored in the main conference, as well as topics of focused interest, including presentations related to international, European and bilateral projects, or other collaborative projects.
The purpose of workshops is to provide a comprehensive forum and encourage in-depth discussion of various technical and application issues in our research field. Workshop registration and venue will be handled as part of the main conference by the EUSIPCO organizers.
The topic coverage, the proposers? credential, the interested audience, and relevance of the topic will all be considered in the selection process. Proposers may be asked to provide additional information, modify part of the proposals, or combine with another one.
Workshop proceedings will be handled by EURASIP and will be publicly available through the repository of EURASIP. Workshop organizers, who have followed a peer-review process and wish to have proceedings, should meet the camera-ready deadline for workshop papers, which is anticipated to be on July 3, 2017. The published workshop papers should follow the EUSIPCO template with a maximum number of pages that will be defined by the Workshop organizers (but it should not be more than 8 pages).
Proposals should be submitted by email to workshops@eusipco2017.org by February 20, 2017. The candidate workshop organizers will be notified of the decision on February 27, 2017.
Proposals should be in PDF format and include the following information:
-Workshop title.
-Proposers? names, titles, affiliations, and primary contact email.
-Experience that makes the proposers well suited for organizing the workshop.
-Topics that will be covered and relevance to the signal processing community.
-Program outline (including preference for half- or full-day event, and if appropriate estimated numbers of orals, posters, and invited talks).
-Names and bios of any tentative/confirmed invited speakers.
-Anticipated target audience as well as expected number of attendees.
-Any special space or equipment requests.
Organizers of each accepted proposal are expected to announce a Call-for-Papers including basic information about the Woskshop (description, main topics, Organizing and Program Committees, important dates).
Organizing Tutorials in the 25th European Signal Processing Conference, EUSIPCO 2017, Kos island, Greece (www.eusipco2017.org) .
Prospective tutorial speakers are invited to submit their proposals via e-mail in PDF by February 17, 2017, to the Tutorials Chairs, Béatrice Pesquet-Popescu and Aggelos Pikrakis (tutorials@eusipco2017.org), indicating:
- Title for the proposed tutorial, its outline and motivation
- List of presenters, including their CVs in a total of at most two pages
- A short description of the tutorial goal, content and the material to be covered
EUSIPCO'2017 tutorial proposals will be judged notably by their technical quality, relevance and timeliness of the topic, quality of the proposal, qualification of the speakers, and presence of similar topics or same speakers at recent EUSIPCOs or other conferences.
Eight half-day tutorials are foreseen which will be held on Monday, August 28, 2017. Tutorials with less than 10 registrations a week after the early registration deadline will not be run unless otherwise explicitly decided by the Tutorials Chairs.
For details regarding the Tutorial Proposal Form, please visit:
Organizing Special Sessions in the 25th European Signal Processing Conference, EUSIPCO 2017, Kos island, Greece (www.eusipco2017.org) .
Prospective Researchers are invited to submit proposals for Special Sessions related to an emerging area in signal processing and to its applications by December 12th 2016, via e-mail in PDF to the Special Session chairs Alex Potamianos and Maurizio Omologo (special_sessions@eusipco2017.org).
EUSIPCO has an excellent track record over the years for organizing Special Sessions in new or emerging areas. This year we are seeking innovative, high-quality and potentially interdisciplinary proposals for Special Sessions that complement the regular program of the conference. Special Sessions should be focused and provide both an overview of the state-of-the-art, as well as highlight the most promising research directions, trends and challenges in the proposed field of signal processing.
Proposers should submit the following information with their submission:
Special Session title
Short description of proposed field (one paragraph)
Novelty and motivation (one to two paragraphs), including why this topic is of interest to the EUSIPCO community
Short biography of the organizers
List of four (4) contributed papers (titles, authors w. affiliations, and a short abstract), excluding state-of-the art review and papers contributed by organizers
Proposals will be evaluated based on topic novelty and associated impact, organizing committee qualifications, as well as the proposed list of contributed papers.
Special Session submissions at EUSIPCO 2017 are reviewed via the same exact process as submissions to the regular program, and papers are expected to meet the same quality standards. For Special Sessions that are somewhat undersubscribed (due to paper rejections or limited number of submissions), an effort will be made to identify regular submission papers to complete the session, as deemed appropriate by the conference organizers. If a Special Session is seriously undersubscribed the Special Session may be canceled, in which case the accepted papers from the canceled Special Session will be placed into the regular program.
(2017-08-31) 1st Speech and Swallowing in Parkinson’s Disease School , Aix-en-Provence,France
Ecole d’été « 1st Speech and Swallowing in Parkinson’s Disease School »
31 août – 2 septembre 2017 Laboratoire Parole et Langage (UMR7309 CNRS AMU), Aix-en-Provence
La « 1st Speech and Swallowing in Parkinson’s Disease School » aura lieu du 31 août au 2 septembre 2017 au Laboratoire Parole et Langage à Aix-en-Provence.
Organisée par la Movement Disorders Society, cette école d'été porte sur les troubles de la parole et de la déglutition liées la maladie de Parkinson, et plus précisément comment les évaluer et les prendre en charge.
Public: orthophonistes, neurologues, professionnels de santé.
**************************** CLEF 2018 Avignon, France - September 10-14, 2018 http://clef2018.clef-initiative.eu/ *****************************
Call for Labs Proposals
CLEF is a leading annual international conference exploring topics in information access technologies. CLEF uniquely combines evaluation laboratories and workshops with research presentations, panels, poster and demo sessions. CLEF 2018 (http://clef2018.clef-initiative.eu/) will be held on 10-14 September 2018 at Avignon University, Avignon, France.
Researchers and practitioners from all areas of information access and related communities are invited to submit proposals for evaluation labs for consideration for inclusion in CLEF 2018. Lab proposals will be reviewed by the lab selection committee. Organizers of selected proposals will be invited to include their lab in the CLEF 2018 lab programme, possibly subject to small suggested modifications to their proposal to better suit the CLEF lab workflow or timeline.
Background
The CLEF Initiative (http://www.clef-initiative.eu/) is a self-organized body whose main mission is to promote research, innovation, and development of information access systems with an emphasis on multilingual information in different modalities - including text and multimedia - with various levels of structure. CLEF promotes research and development by providing an infrastructure for:
independent evaluation of information access systems;
investigation of the use of unstructured, semi-structured, highly-structured, and semantically enriched data in information access;
creation of reusable test collections for benchmarking;
exploration of new evaluation methodologies and innovative ways of using experimental data;
discussion of results, comparison of approaches, exchange of ideas, and transfer of knowledge.
CLEF 2018 will be the ninth edition of the current CLEF conference launched as a continuation of the annual CLEF evaluation campaign series which ran with great success from 2000 to 2009 contributing to the systematic evaluation of information access systems, primarily through experimentation on shared tasks.
Evaluation Labs that are a 'campaign-style' evaluation for specific information access problems (during the twelve month period preceding the conference), similar in nature to the traditional CLEF campaign 'tracks'. Topics covered by campaign-style labs can be inspired by any information access-related domain or task.
Labs that follow a more classical 'workshop' pattern, exploring issues of evaluation methodology, metrics, processes etc. in information access and closely related fields, such as natural language processing, machine translation, and human-computer interaction.
If the organisers of the proposal are new to CLEF or other shared task evaluation campaigns, we highly recommend that a lab workshop first be organised to discuss the format, the problem space, and the practicalities of the shared task. The CLEF 2018 programme will reserve about half of the conference schedule for lab sessions. The labs will present their overall results 'overview presentations' during the plenary scientific paper sessions to allow non-participants to get a sense of where the research frontiers are moving. Organisers of each lab are expected to organise the separate sessions for their lab at the conference so that they contain ample time for general discussion and engagement by all participants - not just those presenting campaign results and papers. Organisers should plan time in their sessions for activities such as panels, demos, poster sessions etc. as appropriate. CLEF is always interested in receiving and facilitating innovative lab proposals. Potential task proposers who are unsure of the suitability of their task proposal or its format for inclusion at CLEF are encouraged to contact the CLEF 2018 Lab Organizing Committee Chairs to discuss its suitability or design at an early stage.
Proposal Submission
Lab proposals must provide sufficient information to judge the relevance, timeliness, scientific quality, benefits for the research community, and the competence of the proposers to co-ordinate the lab. Each lab proposal should identify one or more organizers as responsible for ensuring the timely execution of the lab. Proposals should be 3-4 pages long and should provide the following information:
Title of the proposed lab.
A brief description of the lab topic and goals, its relevance to CLEF and the significance for the field.
A brief but clear statement of usage scenarios or domain to which the activity is intended to contribute, including the evaluation setup and metrics.
Details on the lab organizer(s), including identifying the task chair(s) responsible for ensuring the running of the task. This should include details of any previous of involvement in organising or participating in evaluation tasks at CLEF or similar campaigns.
The planned format of the lab, i.e. campaign-style ('track') or workshop.
Is the lab a continuation of an activity from previous year(s) or a new activity? a. For activities continued from previous year(s): Statistics from previous years (number of participants/runs for each task), a clear statement on why another edition is needed, an explicit listing of the changes proposed, and a discussion of lessons to be learned or insights to be made. b. For new activities: A statement on why a new evaluation campaign is needed and how the community would benefit from the activity.
Details of the expected target audience, i.e. who do you expect to participate in the task(s), and how do you propose to reach them.
Brief details of tasks to be carried out in the lab. The proposal should clearly motivate the need for each of the proposed tasks and provide evidence of its capability of attracting enough participation. The dataset which will be adopted by the Lab needs to be described and motivated in the perspective of the goals of the Labs; also indications on how the dataset will be shared are useful. It is fine for a lab to have a single task, but labs often contain multiple closely related tasks, needing a strong motivation for more than 3 tasks, to avoid useless fragmentation.
Expected length of the lab session at the conference: half-day, one day, two days. This should include very high level details of planned structure of the session, e.g. participant presentations, invited speaker(s), panels, etc., to justify the requested session length.
Arrangements for the organization of the lab campaign: who will be responsible for activities within the task; how will data be acquired or created, what tools or methods will be used, e.g., how will necessary queries be created or relevance assessment carried out; any other information which is relevant to the conduct of your lab.
If the lab proposes to set up a steering committee to oversee and advise its activities, include names, addresses, and homepage links of people you propose to be involved.
Reviewing Process
Each submitted proposal will be reviewed by the CLEF 2018 lab organizing committee. The decision will be sent by email to the responsible organizer by September 13, 2017. The final length of the lab session will be determined based on the overall organization of the conference and the number of participant submissions received by a lab. Organizers of accepted labs are expected to announce and briefly present their lab at the final session of CLEF 2017 on the 14 September in Dublin, Ireland.
April 15, 2017 ......... Submission of full papers (final date)
May 15, 2017 ............. Notification of acceptance
May 26, 2017 ............. Final papers (camera ready)
May 26, 2017 ............. Early registration
Sept 12-16, 2017 ??? Conference dates
TOPICS
The SPECOM conference is devoted to issues of human-machine interaction, particularly:
Affective computing; Applications for human-machine interaction; Audio-visual speech processing; Automatic language identification; Corpus linguistics and linguistic processing; Forensic speech investigations and security systems; Multichannel signal processing; Multimedia processing; Multimodal analysis and synthesis; Signal processing and feature extraction; Speaker identification and diarization; Speaker verification systems; Speech analytics and audio mining; Speech and language resources; Speech dereverberation; Speech disorders and voice pathologies; Speech driving systems in robotics; Speech enhancement; Speech perception; Speech recognition and understanding; Speech translation automatic systems; Spoken dialogue systems; Spoken language processing; Text mining and sentiment analysis; Text-to-speech and speech-to-text systems; Virtual and augmented reality.
Special Session 1: Natural Language Processing for Social Media Analysis
The exploitation of natural language from social media data is an intriguing task in the fields of text mining and natural language processing (NLP), with plenty of applications in social sciences and social media analytics. In this special session, we call for research papers in the broader field of NLP techniques for social media analysis. The topics of interest include (but are not limited to): sentiment analysis in social media and beyond (e.g., stance identification, sarcasm detection, opinion mining), computational sociolinguistics (e.g., identification of demographic information such as gender, age), and NLP tools for social media mining (e.g., topic modeling for social media data, text categorization and clustering for social media).
Organisers:
Vasiliki Simaki and Carita Paradis (Lund University, Sweden)
Special Session 2: Multilingual and Low-Resourced Languages Speech Processing in Human-Computer Interaction
Multilingual speech processing has been an active topic for many years. Over the last few years, the availability of big data in a vast variety of languages and the convergence of speech recognition and synthesis approaches to statistical parametric techniques (mainly deep learning neural networks) have put this field in the center of research interest, with a special attention for low- or even zero-resourced languages. In this special session, we call for research papers in the field of multilingual speech processing. The topics include (but are not limited to): multilingual speech recognition and understanding, dialectal speech recognition, cross-lingual adaptation, text-to-speech synthesis, spoken language identification, speech-to-speech translation, multi-modal speech processing, keyword spotting, emotion recognition and deep learning in speech processing.
Organisers:
Alexandros Lazaridis (Idiap Research Institute, Switzerland)
Ivan Himawan (Queensland University of Technology, Australia)
Blaise Potard (CereProc Ltd, Edinburgh, UK)
Kate Knill (Cambridge University Engineering Department)
Peter Bell (University of Edinburgh, UK)
Special Session 3: Real-Life Challenges in Voice and Multimodal Biometrics
Complex passwords or cumbersome dongles are now obsolete. Biometric technology offers a secure and user friendly solution to authenticate and have been employed in various real-life scenarios. This special session seeks to bring together researchers, professionals, and practitioners to present and discuss recent developments and challenges in Real-Life applications of biometrics. Topics of interest include (but are not limited to):
Biometric systems and applications; Identity management and biometrics; Fraud prevention; Anti-spoofing methods; Privacy protection of biometric systems; Uni-modalities, e.g. voice, face, fingerprint, iris, hand geometry, palm print and ear biometrics; Behavioural biometrics; Soft-biometrics; Multi-biometrics; Novel biometrics; Ethical and societal implications of biometric systems and applications.
Organisers:
Saeid Safavi (School of Engineering and Technology, University of Hertfordshire, UK)
Lily Meng (School of Engineering and Technology, University of Hertfordshire, UK)
Maryam Najafian (CSAIL Lab, Massachusetts Institute of Technology, USA)
Mohamad Hassan Bahari (Centre for processing speech and images, KU Leuven, Belgium)
Abosoud Hanani (Department of Computer Systems Engineering, Birzeit University, Palestine)
Hossein Zeinali (Computer and Engineering Department, Sharif University of Technology, Iran)
Invited Speakers
Prof Mark Gales, University of Cambridge: ?Low-Resource Speech Recognition and Keyword-Spotting?.
Prof Björn Schuller, University of Passau and Imperial College London: ?Big Data, Deep Learning ? At the Edge of X-Ray Speaker Analysis?.
We invite everyone from academia and industry to submit to the shared task on German Sentiment Analysis!
**** Jun 2017 Updates *** *** Evaluation script for download *** Java baseline system available ****
---- Introduction ----
In the connected, modern world, customer feedback is a valuable source for insights on the quality of products or services. This feedback allows other customers to benefit from the experiences of others and enables businesses to react on requests, complaints or recommendations. However, the more people use a product or service, the more feedback is generated, which results in the major challenge of analyzing huge amounts of feedback in an efficient, but still meaningful way.
We conduct a shared task on automatically analyzing customer reviews about ?Deutsche Bahn? - the German public train operator with about two billion passengers each year. The task is associated with the GSCL 2017 conference in Berlin, and will take place there as a workshop on September 12, 2017.
---- Data ---- The data for the task has been annotated as part of a joint project between TU Darmstadt and Deutsche Bahn, see https://sites.google.com/view/germeval2017-absa/data for details. All together it consists of 22,000 messages from various social media and web sources. The data is annotated with relevance, document sentiment, aspect-based sentiment and opinion target expressions and is provided in both xml and tsv.
---- Task description ----
To exploit the richness of the data, we subdivided the task into four subtasks. Participants can freely choose in what and how many sub-tasks they participate.
Subtask A) Relevance Classification Determine whether a social media post contains feedback about the 'Deutsche Bahn' or if the post is off-topic/contains no evaluation. Example: ?Ehrlich die männer in Der Bahn haben keine manieren?? In the given post, the task is to identify that the post is 'relevant'.
Subtask B) Document-level Polarity Identify, whether the customer evaluates the 'Deutsche Bahn' or travel as positive, negative or neutral. Example: 'Ingo Lenßen Guten morgen Ingo...bei mir kein regen aber bahn fehr wieder nicht...' In the given post, the task is to identify the posts' polarity : negative
Subtask C) Aspect-level Polarity Identify all aspects which are positively and negatively evaluated within the review. In order to increase comparability, the aspects are previously divided into predefined categories. Consequently, the aim of the subtasks is to identify all contained categories and their associated polarity. Example: ?Alle so 'Yeah, Streik beendet'' Bahn so 'Okay, dafür werden dann natürlich die Tickets teurer' Alle so 'Können wir wieder Streik haben??? In the given post, the task is to identify the aspects and their polarity: < Ticketkauf#Haupt:negativ> <allgemein#Haupt:positive>
Subtask D) Opinion Target Extraction Identify the linguistic expression in the posts which are used to express the aspect-based sentiment (subtask C). The opinion target expression is defined by its starting and ending offsets. Example: @m_wabersich IC 2151? Der fährt nicht. Ich habe Ihnen die Alternative bereits genannt. /je In the given post the task ist to identify the target expression <fährt nicht> (from='26' to='37').
The organizers provide a baseline system and an evaluation method that may be used to lower the obstacles for participation. For both the baseline system and the evaluation method the organisers release executables and open-source code to enable an easy integration into the participating systems: - baseline system + instructions : https://github.com/uhh-lt/GermEval2017-Baseline - evaluation method + instructions: https://github.com/muchafel/GermEval2017
Participating team/participants may submit several runs.
Submissions consist of one TSV or XML file per subtask providing predictions for the test data and a paper of 4 pages (excluding references) describing the chosen approach and analyzing the performance. Each participating team/participant should submit only one paper regardless of how many subtasks they participate in; per subtask, participants can add 1 page to the paper, up to a maximum of 7 pages. Papers should follow the GSCL 2017 style files. We expect authors to present summaries of their systems at the GSCL workshop and to participate in the discussions.
---- Important Dates ----
* March 2017 Release of Trial Data * April 2017 Release of Training Data * July 24, 2017 Release of Test Data * August 14, 2017 Submission of System Runs * August 21, 2017 Submission of System Description papers * September 1, 2017 Feedback on System Description papers * September 8, 2017 Final Submission of System Description papers * September 12, 2017 Workshop co-located with GSCL 2017
---- Organizing committee ----
* Chris Biemann, Language Technology, Uni Hamburg, biemann[at]informatik.uni-hamburg.de * Eugen Ruppert, Language Technology, Uni Hamburg, ruppert[at]informatik.uni-hamburg.de * Michael Wojatzki, Language Technology Lab, Uni Duisburg-Essen, michael.wojatzki[at]uni-due.de * Torsten Zesch, Language Technology Lab, Uni Duisburg-Essen, torsten.zesch[at]uni-due.de
We encourage all interested teams to join the GermEval 2017 ABSA mailing list at https://groups.google.com/forum/#!forum/germeval2017-absa, which will be the primary source for updates on dates and test conditions. To contact the organizing committee, please post to this mailing list or send an e-mail to Michael Wojatzki for private communication.
(2017-09-20) 11th Oxford Dsfluency Conference (ODC), Oxford, UK (Now program on line)
In 2017 the goal of the 11th Oxford Dysfluency Conference (ODC) is to encourage discussion and debate that will challenge and enhance our perspectives and understanding of research; the nature of stuttering and / or cluttering; and management across the ages.
We would like to remind you to submit your oral and poster abstracts on the conference topics below. Please submit via the abstract submission system by the 31 March 2017.
New perspectives on assessment and therapy: -Issues, variables, and controversies in assessment and outcome
in children
in adolescents
in adults
Supporting the next generation of clinicians and researchers
We are giving junior researchers at the start of their research career the opportunity to present and discuss their research plans or current results to a panel of international specialists in a supportive, constructive, and dynamic environment. For more information please visit our website.
We look forward to meeting you in Oxford!
Regards,
Conference Chairs Sharon Millard, The Michael Palin Centre for Stammering, UK Shelley B. Brundage, George Washington University, USA
To receive email updates for this event please sign up now! For further information and to register for email updates visit: www.dysfluencyconference.com
Convenor: Robert Fuchs (Hong Kong Baptist University)
Speech rhythm has long been recognised as an important supra-segmental category of speech, yet its measurement, relevance and the theoretical soundness of the concept continue to be hotly debated. The arguably most widely supported approach considers speech rhythm to consist of a continuum ranging from (1) a syllable-timed pole, with relatively small differences in prominence between syllables, to (2) a stress-timed pole, with relatively large differences in prominence between syllables. Most L1 varieties of English are widely regarded to be more stress-timed than most L2 and learner varieties, and this is supported by a considerable amount of empirical evidence (e.g. Deterding 1994, 2001, Fuchs 2016, Gut 2005, Gut and Milde 2002, Low 1998).
Yet, upon closer inspection, many of the concepts underlying this research appear to be contested. For one, L1 varieties of English are themselves heterogeneous in their rhythm. There is, for example, regional variation, with some dialects spoken in the British Isles being more syllable-timed than others (Ferragne 2008, Ferragne and Pellegrino 2004, White and Matty 2007a, 2007b, White et al. 2007). Similarly, in L2 varieties, sociolinguistic differences such as that between acrolect and basilect might go hand in hand with a difference in speech rhythm. As for learner Englishes, while there is good evidence of the transfer of rhythmic characteristics from L1 to L2 (e.g. Dellwo et al. 2009, Gut 2009, Jang 2008, Sarmah et al. 2009), more research is needed to show that this has consequences in terms of foreign accent and accent recognition. More generally, research on speech rhythm would benefit from studies showing that quantitative measures of speech rhythm (so-called rhythm metrics) are perceptually relevant and psychologically ?real? in the sense that what is measured is reflected in a certain kind of percept. Finally, the very nature and reliability of these rhythm metrics has been discussed extensively, but arguably inconclusively, in the past years, with some researchers attempting to identify those duration-based metrics that are most reliable (White and Mattys 2007a, White et al.2007, Wiget et al. 2010), others concluding that none of them are reliable (Arvaniti 2009, 2012, Arvaniti et al. 2008), and yet others suggesting metrics that focus on acoustic correlates of prominence other than duration, such as intensity (Fuchs 2016, He 2012, Low 1998), loudness (Fuchs 2014a), f0 (Cumming 2010, 2011, Fuchs 2014b) and sonority (Galves et al. 2012).
In order to address these issues, this workshop aims to bring together researchers working on one or more of the following aspects:
Applications of rhythm metrics that measure speech rhythm based on acoustic correlates of prominence other than duration
Comparative tests of the validity and reliability of existing rhythm metrics
Perceptual relevance and psychological reality of speech rhythm
Relevance of speech rhythm in Second Language Acquisition/learner Englishes, e.g. its contribution to foreign accent as well as pedagogical approaches
Differences in speech rhythm between varieties previously thought to be in the same 'rhythm class'
Sociolinguistic relevance of speech rhythm in indexing e.g. lectal differences or ethnic subvarieties within the same national variety of English
Apart from addressing one or more of the issues above, papers need be concerned with (a variety of) English or a language contact situation involving English (in keeping with the scope of the conference).
The workshop will consist of full papers and work in progress reports, which will be allotted 20 minutes for presentation (plus 10 minutes for discussion). The deadline for submission of abstracts (ca. 500 words, excluding title, references and keywords) is 15 December 2016. Notification of acceptance will be sent out by the end of January 2017. Abstracts should be sent to rfuchs@hkbu.edu.hk .
References
Arvaniti, Amalia. 2009. Rhythm, timing and the timing of rhythm. Phonetica 66(1/2): 46?63.
Arvaniti, Amalia. 2012. The usefulness of metrics in the quantification of speech rhythm. Journal of Phonetics 40: 351?373.
Arvaniti, Amalia, Tristie Ross, and Naja Ferjan. 2008. On the reliability of rhythm metrics. Journal of the Acoustical Society of America 124(4): 2495.Dellwo, Volker, Francisco Gutiérrez Diez, and Nuria Gavalda. 2009. The development of measurable speech rhythm in Spanish speakers of English. In Actas de XI Simposio Internacional de Comunicacion Social, Santiago de Cuba, 594?597.
Cumming, Ruth E. 2010. The language-specific integration of pitch and duration. PhD thesis. University of Cambridge.
Cumming, Ruth E. 2011. Perceptually informed quantification of speech rhythm in pairwise variability indices. Phonetica 68(4): 256?277.
Deterding, David. 1994. The rhythm of Singapore English. In Proceedings of the fifth Australian international conference on speech science and technology, ed. Roberto Togneri, 316?321. Perth: Uniprint.
Deterding, David. 2001. The measurement of rhythm: A comparison of Singapore and British English. Journal of Phonetics 29: 217?230.
Ferragne, Emmanuel. 2008. Etude Phonétique des Dialectes Modernes de l?Anglais des Iles Britanniques: Vers l?Identification Automatique du Dialecte. PhD thesis. Université Lumière Lyon 2.
Ferragne, Emmanuel, and François Pellegrino. 2004. A comparative account of the suprasegmental and rhythmic features of British English dialects. Actes de Modelisations pour l?Identification des Langues, Paris, 121?126.
Fuchs, Robert. 2014a. Integrating variability in loudness and duration in a multidimensional model of speech rhythm: Evidence from Indian English and British English. In Proceedings of speech prosody 7, Dublin, ed. Nick Campbell, Dafydd Gibbon, and Daniel Hirst, 290?294.
Fuchs, Robert. 2014b. Towards a perceptual model of speech rhythm: Integrating the influence of f0 on perceived duration. In Proceedings of interspeech 2014, ed. Haizhou Li, Helen Meng, Bin Ma, Eng Siong Chng, and Lei Xie, Singapore, 1949?1953.
Fuchs, Robert. 2016. Speech Rhythm in Varieties of English: Evidence from Educated Indian English and British English. Singapore: Springer.
Galves, Antonio, Jesus Garcia, Denise Duarte, and Charlotte Galves. 2002. Sonority as a basis for rhythmic class discrimination. In Proceedings of speech prosody 2002, Aix-en-Provence, 323?326.
Gut, Ulrike. 2005. Nigerian English prosody. English World-Wide 26(2): 153?177.
Gut, Ulrike. 2009. Non-native speech. A corpus-based analysis of phonological and phonetic properties of L2 English and German. Frankfurt: Peter Lang.
Gut, Ulrike, and Jan-Torsten Milde. 2002. The prosody of Nigerian English. In Proceedings of the speech prosody 2002 conference, ed. Bel Bell and Isabelle Marlien, 367?370. Aix-en-Provence: Laboratoire Parole et Langage.
He, Lei. 2012. Syllabic intensity variations as quantification of speech rhythm: Evidence from both L1 and L2. In Proceedings of the 6th international conference on speech prosody, Shanghai, 22?26 May 2012, ed. Qiuwu Ma, Hongwei Ding, and Daniel Hirst, 466?469. Shanghai: Tongji University Press.
Jang, Tae-Yeoub. 2008. Speech rhythm metrics for automatic scoring of English speech by Korean EFL learners. Malsori Speech Sounds 66: 41?59.
Low, Ee Ling. 1998. Prosodic Prominence in Singapore English. PhD thesis. University of Cambridge.
Sarmah, Priyankoo, Divya Verma Gogoi, and Caroline Wiltshire. 2009. Thai English. Rhythm and vowels. English World-Wide 30(2): 196?217.
White, Laurence, and Sven L. Mattys. 2007a. Calibrating rhythm: First language and second language studies. Journal of Phonetics 35(4): 501?522.
White, Laurence, and Sven L. Mattys. 2007b. Rhythmic typology and variation in first and second languages. Segmental and Prosodic Issues in Romance Phonology 282: 237?257.
White, Laurence, Sven L. Mattys, Lucy Series, and Suzi Gage. 2007. Rhythm metrics predict rhythmic discrimination. In Proceedings of the 16th international congress of phonetic sciences, Saarbrücken, 1009?1012.
Wiget, Klaus, Laurence White, Barbara Schuppler, Izabelle Grenon, Oleysa Rauch, and Sven L. Mattys. 2010. How stable are acoustic metrics of contrastive speech rhythm? Journal of the Acoustical Society of America 127(3): 1559?1569.
(2017-10-16) 11th International Seminar on Speech Production (ISSP-2017), Tianjin, China
We take great pleasure to invite you to submit research article in the 11th International Seminar on Speech Production (ISSP-2017) which will be held on October 16-19, 2017 in Tianjin, China. ISSP is a triennial conference with the aim of providing an interdisciplinary forum for researchers working on all aspects of speech production from fields as diverse as phonology, phonetics, prosody, mechanics, acoustics, physiology, motor control, neuroscience, computer science and human interaction. ISSP has been held over the word since 1988.
The ISSP-2017 will be hosted by Tianjin University and Institute of Linguistics of Chinese Academy of Social Sciences. Tianjin was the ancient port city to Beijing, and is the 3rd largest city of China with a population of over 15 million. It has a rich history and remains characteristics of old British and Italian architecture. The famous Italian concession area has the largest cluster of old Italian architecture outside of Italy. Located 85 miles east of Beijing, Tianjin is the largest coastal city in northern China. Tianjin is now a modern, developed city. Tianjin has a reputation throughout China for being extremely friendly, safe and a place of delicious food. Welcome to Tianjin.
The proceeding will be published by Springer and indexed by EI. Papers with high quality will be included in a special issue of ?Journal of Speech, Language, and Hearing Research?/ ?Journal of Phonetics? after revision.
Topics of interest for submission include, but are not restricted to the following:
? Perception-action control ? Intra- and inter-speaker variability ? Articulatory synthesis ? Mapping between articulatory and acoustic events ? Acoustic-to-articulatory inversion ? Coarticulation ? Prosody ? Biomechanical modeling ? Models of motor control ? Audiovisual synthesis ? Aerodynamic models ? Cerebral organization and neural correlates of speech ? Disorders of speech motor control ? Instrumental techniques ? Speech and language acquisition ? Audio-visual speech perception ? Plasticity of speech production and perception
For more information about ISSP2017, please refer to the conference webpage: www.issp2017.org.cn
Important Dates:
2-page abstract submission deadline 1 March 2017
Notification of paper acceptance 1 May 2017
Full paper upload deadline 1 August 2017
Author?s registration deadline 1 September 2017
best
-- Qiang Fang Phonetics Lab. Institute of Linguistics, Chinese Academy of Social Sciences No.5, Jian Guo Men Nei Da Jie, Beijing, China
Co-located with the seventh International Conference on Affective Computing and Intelligent Interaction ACII 2017 (http://acii2017.org/), San Antonio, Texas October 23, 2017
***Submission deadline: June 15, 2017***
Keynote speaker: Georgios Yannakakis, Institute of Digital Games, Univ. of Malta
*NEWS*
- ESSEM 2017 is supported by: CELI Language Technology - https://www.celi.it/en/ - Workshop Proceedings will be published by IEEE Xplore (indexed by Scopus)
The role of emotional intelligence is increasing at fast speed in everyday computer-mediated interactions, thanks to the integration of more or less explicit affective elements in social networks, apps, virtual assistants, etc. Expressed through emojis, color, tags or speech, affect has become part of our relationships with computers, adding depth and involvement to them. The technical advancement of the available expressive means, from 3D to language technologies, is one of the key factors of this process. ESSEM 2017 addresses the expression of emotions in many-to-many interaction and in one-to-one interaction as a tool for promoting, analysing and measuring user engagement. In particular, we are interested in tools and models that rely on NLP, acoustic and video analysis; theories and methods that bridge the expression of emotions from language to media are especially needed to overcome the limitations of language-specific and media-specific approaches. ESSEM 2017 focuses on interaction as a testbed for the models and tools developed for social and expressive media. The ultimate goal is to devise socio-emotional strategies to foster user engagement. We encourage contributions on applications that specifically address the role of sentiment and emotions in the interactions that occur through social and expressive media, with a special focus on cultural heritage, artistic expression, education and entertainment (e.g., storytelling, artistic curation, audience development, games and edutainment). ESSEM aims at bringing together researchers and practitioners both from academia and industry. It wants to take an active part in growing a new field in terms of multidisciplinary research and to investigate open issues by cross-validating different approaches in emotion research. Topics include, but are not limited to:
- Affect-related phenomena in social media - Affect-related phenomena in expressive media - Affect-related phenomena in the user's engagement process - Subjectivity, sentiments and emotions in social & expressive media - Affect and figurative language, stance or deception in social & expressive media - Design of engaging agents - Socio-emotional strategies for user engagement - User engagement in human-human and human-agent interactions using NLP & audio-video analysis - Grounding affect in conversational context - Affect and regulation of human-agent interaction - Affect and emotions in embodiment - Affect in interactive entertainment (drama, storytelling, games, etc.) and art (artistic curation, audience development, etc.) - Applications of affective computing in multimodal interaction - Applications of sentiment analysis and emotion detection in social & expressive media
*Important dates*
- June 15, 2017: Paper submission deadline - July 15, 2017: Notification of acceptance - August 18, 2017: Final manuscripts due (hard deadline for all workshops) - Workshop date: October 23, 2017)
*Paper submission*
Standard research papers should be a maximum of 6 pages long. We also encourage submission of short research papers (including opinion statements) of maximum 3 pages long. Submissions must be anonymous and follow the ACII 2017 formatting guidelines: http://acii2017.org/submission
Workshop Proceedings will be published by IEEE Xplore.
*Organizers*
Cristina Bosco, University of Torino, Italy Erik Cambria, Nanyang Technological University, Singapore Chloé Clavel, LTCI, Telecom-ParisTech, Paris-Saclay University, Paris, France Rossana Damiano, University of Torino, Italy Viviana Patti, University of Torino, Italy Paolo Rosso, Technical University of Valencia, Spain
*Programme Committee*
Alexandra Balahur, European Commission Joint Research Centre Andrea Bolioli, CELI, Italy Zoraida Callejas, University of Granada, Spain Lea Canales, Universitat d?Alacant, Spain Paula Carvalho, University of Lisbon, Portugal Marc Cavazza, Teesside University, UK Antonio Chella, University of Palermo, Italy Giuseppe Riccardi, University of Trento, Italy Dipankar Das, Jadavpur University, India Berardina Nadja De Carolis, University of Bari Aldo Moro, Italy Guillaume Dubuisson-Duplessis, Telecom-ParisTech, Paris-Saclay University, France Elisabetta Fersini, University of Milano-Bicocca, Italy Dirk Heylen, University of Twente, The Netherlands Carlos A. Iglesias, Universidad Politécnica de Madrid, Spain Aditya Joshi IITB-Monash Research Academy, Mumbai, India Emiliano Lorini, IRIT-CNRS, Toulouse, France Alessandro Moschitti, University of Trento, Italy Malvina Nissim, University of Groningen, the Netherlands Nicole Novielli, University of Bari Aldo Moro, Italy Magalie Ochs, LSIS, University of Aix Marseille, France Paolo Petta, Austrian Research Institute for Artificial Intelligence, Austria Rémi Ronfard, INRIA, France Saif Mohammad, National Research Council, Canada Björn Schuller, University of Passau, Germany, Imperial College London, UK Candace Sidner, WPI, US Mariët Theune, University of Twente, The Netherlands Marko Tkalcic, Free University of Bozen, Italy Serena Villata, INRIA Sophia Antipolis, France Emilio Vivancos, UPV, Spain Gualtiero Volpe, University of Genova, Italy Enrico Zovato, Nuance Communications, USA
(2017-10-23) 5th INTERNATIONAL CONFERENCE ON STATISTICAL LANGUAGE AND SPEECH PROCESSING (SLSP 2017), Le Mans, France (updated)
5th INTERNATIONAL CONFERENCE ON STATISTICAL LANGUAGE AND SPEECH PROCESSING SLSP 2017 Le Mans, France October 23-25, 2017 Organized by: Computer Science Lab (LIUM) University of Le Mans Research Group on Mathematical Linguistics (GRLMC) Rovira i Virgili University http://grammars.grlmc.com/SLSP2017/ ********************************************************************************** AIMS: SLSP is a yearly conference series aimed at promoting and displaying excellent research on the wide spectrum of statistical methods that are currently in use in computational language or speech processing. It aims at attracting contributions from both fields. Though there exist large, well-known conferences and workshops hosting contributions to any of these areas, SLSP is a more focused meeting where synergies between subdomains and people will hopefully happen. In SLSP 2017, significant room will be reserved to young scholars at the beginning of their career and particular focus will be put on methodology. VENUE: SLSP 2017 will take place in Le Mans, in the region Pays de la Loire, a city with well-preserved Gallo-Roman remnants. The venue will be: Claude Chappe Informatics Institute University of Le Mans Avenue Laënnec 72085 Le Mans Cedex 9 SCOPE: The conference invites submissions discussing the employment of statistical models (including machine learning) within language and speech processing. Topics of either theoretical or applied interest include, but are not limited to: anaphora and coreference resolution authorship identification, plagiarism and spam filtering computer-aided translation corpora and language resources data mining and semantic web information extraction information retrieval knowledge representation and ontologies lexicons and dictionaries machine translation multimodal technologies natural language understanding neural representation of speech and language opinion mining and sentiment analysis parsing part-of-speech tagging question-answering systems semantic role labelling speaker identification and verification speech and language generation speech recognition speech synthesis speech transcription spelling correction spoken dialogue systems term extraction text categorisation text summarisation user modeling STRUCTURE: SLSP 2017 will consist of: invited talks peer-reviewed contributions posters INVITED SPEAKERS: tba PROGRAMME COMMITTEE: (to be completed) Robert Gaizauskas (University of Sheffield, UK) Keikichi Hirose (University of Tokyo, JP) Gareth Jones (Dublin City University, IE) Tomi Kinnunen (University of Eastern Finland, FI) Elizabeth D. Liddy (Syracuse University, US) Xunying Liu (Chinese University of Hong Kong, HK) Carlos Martín-Vide (Rovira i Virgili University, ES, chair) Yuji Matsumoto (Nara Institute of Science and Technology, JP) Marie-Francine Moens (KU Leuven, BE) Preslav Nakov (Qatar Computing Research Institute, QA) Hermann Ney (RWTH Aachen University, DE) Holger Schwenk (Facebook, FR) Phil Woodland (University of Cambridge, UK) ORGANIZING COMMITTEE: Walid Aransa (Le Mans) Adrien Bardet (Le Mans) Abdessalam Bouchekif (Le Mans) Fethi Bougares (Le Mans) Nathalie Camelin (Le Mans) Yannick Estève (Le Mans, co-chair) Mercedes García Martínez (Le Mans) Sahar Ghannay (Le Mans) Anthony Larcher (Le Mans) Antoine Laurent (Le Mans) Carlos Martín-Vide (Tarragona, co-chair) Salima Mdhaffar (Le Mans) Manuel J. Parra Royón (Granada) Simon Petitrenaud (Le Mans) David Silva (London) Natalia Tomashenko (Le Mans) Kévin Vythelingum (Le Mans) SUBMISSIONS: Authors are invited to submit non-anonymized papers in English presenting original and unpublished research. Papers should not exceed 12 single-spaced pages (including eventual appendices, references, proofs, graphics, etc.) and should be prepared according to the standard format for Springer Verlag's LNCS series (see http://www.springer.com/computer/lncs?SGWID=0-164-6-793341-0). Submissions have to be uploaded to: https://easychair.org/conferences/?conf=slsp2017 PUBLICATIONS: A volume of proceedings published by Springer in the LNCS/LNAI series will be available by the time of the conference. A special issue of a major journal will be later published containing peer-reviewed substantially extended versions of some of the papers contributed to the conference. Submissions to it will be by invitation. REGISTRATION: The registration form can be found at: http://grammars.grlmc.com/SLSP2017/Registration.php DEADLINES (all at 23:59 CET): Extended paper submission: June 18, 2017 Notification of paper acceptance or rejection: July 11, 2017 Final version of the paper for the LNCS/LNAI proceedings: July 21, 2017 Early registration: July 21, 2017 Late registration: October 9, 2017 Submission to the journal special issue: January 25, 2018 QUESTIONS AND FURTHER INFORMATION: david.silva409@yahoo.com POSTAL ADDRESS: SLSP 2017 Research Group on Mathematical Linguistics (GRLMC) Rovira i Virgili University Av. Catalunya, 35 43002 Tarragona, Spain ACKNOWLEDGMENTS: Université du Maine Universitat Rovira i Virgili
The Association for the Advancement of Affective Computing (AAAC) invites you to join us at our seventh International Conference on Affective Computing and Intelligent Interaction (ACII), which will be held in San Antonio, Texas on October 23-26, 2017. The Conference series is the premier international forum for interdisciplinary research on the design of systems that can recognize, interpret, and simulate human emotions and related affective phenomena.
A selection of the best articles will appear in a “Best of ACII2017” special section of IEEE’s Transactions on Affective Computing. Proceedings will be submitted for inclusion to IEEE Xplore. The theme of ACII2017 is “Affective Computing in Action,” highlighting the impact of affective computing technologies in the wider world.
Program
ACII2017 will feature a broad program, with regular talks, posters, demos, workshops, special sessions, a doctoral consortium, special industry panel session on affective computing applications and keynote talks by James Russell (Boston College), Tanzeem Choudhury (Cornell University) and Thomas R. Insel (former NIHM). We will have two special sessions: “Emotions in Cognition, Adaptive Behavior and Action Selection” and “Utilising Big Unlabelled and Unmatched Data for Affective Computing”.
Topics
Topics of interest include, but are not limited to:
Recognition of Human Affect: Uni- or multimodal recognition of affect from face, body, gesture, voice text, or physiology; affective face/body animation; expression and gesture recognition; sentiment analysis
Synthesis of Human Affect: Affective speech synthesis, modeling and animation, synthesis of auditory affect bursts, synthesis of multimodal affective behavior
Affective Interfaces: Affective brain-computer interfaces, design of affective loop and affective dialog systems; mobile, tangible, haptic and virtual/augmented interfaces; affectively-smart environments; affectively proactive interfaces
Social and Behavioral Science Involving Affective Computing: Cognitive affective models; models of moral decision-making; tools for social science research; computational models of emotion; psychological factors in affective computing (personality, culture); ethical issues; dyadic and group affective processes
Affective and Social Robotics and Virtual Agents: Emotions in robot cognition and action, embodied issues in emotion; affective virtual agents; memory, reasoning, and learning of affective systems; affective architectures for virtual & robotic systems
(2017-11-13) CfP Colloque « Corpus oraux, corpus écrits : pratiques croisées », Montpellier France
Appel à communication
Colloque « Corpus oraux, corpus écrits : pratiques croisées », 13 et 14 novembre 2017, Université Paul Valéry, Montpellier 3 Lieu : Site de Saint-Charles 2, Université Paul Valéry, Montpellier 3
Le projet CORAL, les laboratoires PRAXILING (UMR 5267) et DIPRALANG (EA 739) organisent conjointement un colloque intitulé « Corpus oraux, corpus écrits : pratiques croisées », qui aura lieu les 13 et 14 novembre 2017 sur le site Saint Charles.
Les conférenciers invités sont Stefan Evert (FAU Erlangen-Nürnberg), Bente Maegaard (Centre for Language Technologie, University of Copenhagen), Damon Mayaffre (BCL UMR 7320, Université Nice Sophia Antipolis) et Christophe Parisse (Modyco UMR 7114, Université Paris Ouest Nanterre).
L?objectif de ce colloque est de faire dialoguer ces différentes communautés de chercheurs, qu?ils soient producteurs ou utilisateurs de ressources et/ou d?outils. Les approches méthodologiques qui associent différents modes d?exploitation et d?analyse de corpus oraux et écrits seront particulièrement attendues. Il s?agira notamment d?aborder les problématiques suivantes : - Annotation (phonétique, prosodique, gestuelle, morphosyntaxique, sémantique, etc.) ; - Standardisation des annotations et du balisage ; - Mise en place d?un format commun aux corpus écrits et oraux, permettant d?assurer l?interopérabilité entre les deux types de données ; - Exploitation automatique ou semi-automatique et analyse des données ; - Mutualisation des ressources (corpus annotés, schémas d?annotation, lexiques, patrons ou grammaires?) ; - Adaptation et/ou création d?applications pour le traitement et l?exploitation des données orales et écrites.
Format des communications : Les interventions pourront se faire dans trois formats différents : communication orale de 20 minutes, posters et/ou démo (corpus, applications, etc.). Il sera possible de combiner la présentation d?un poster avec une démo. Il est demandé aux auteurs d?exprimer leur préférence au moment de la soumission.
Modalités de soumission : Les propositions doivent être envoyées à l?adresse suivante : coralmontpellier3@univ-montp3.fr avant le 30 juillet 2017. Elles prendront la forme d?un résumé anonymisé (en français ou en anglais) d?une longueur maximale de 500 mots (bibliographie non comprise) au format pdf (en Times New Roman 12). Dans le corps du message, doivent être indiqués le nom, prénom et l?affiliation de l?auteur.
The 19th International Conference on Multimodal Interaction (ICMI 2017) will be held in Glasgow, Scotland. ICMI is the premier international forum for multidisciplinary research on multimodal human-human and human-computer interaction, interfaces, and system development. The conference focuses on theoretical and empirical foundations, component technologies, and combined multimodal processing techniques that define the field of multimodal interaction analysis, interface design, and system development.
The ICMI 2017 Demonstrations & Exhibits session is intended to provide a forum to showcase innovative implementations, systems and technologies demonstrating new ideas about interactive multimodal interfaces. We particularly encourage demonstration of interactive and multimodal analysis systems and sensors. They can also serve to introduce commercial products.
Proposals may be of two types: demonstrations and exhibits. The main difference is that demonstrations include a short paper (2 pages), which will be included in ICMI proceedings, while the exhibits only need to include a short outline (no more than 1 page). We encourage both the submission of early research prototypes and interesting mature systems. In addition, authors of accepted regular research papers are invited to participate in the demonstration sessions as well.
This year will feature a Multimodal Resources track to showcase novel corpora, annotation tools and schemes. Demonstrations in this track will benefit from more exposure to visitors, and will allow visitors to interact with the material.
Demo Submission
A 1-2 page description of the demonstration is required, which must be submitted electronically through the main ICMI conference management system (https://precisionconference.com/~icmi). Demo description(s) must be in PDF format, according to the ACM conference format, of no more than 2 pages in length including references (template available at: http://www.acm.org/publications/proceedings-template#aL2). Demo proposals should include a description with photographs and/or screen captures of the demonstration and, if possible, the URL of a website where a live version or video of the proposed demo is available. Please note that the accepted descriptions will be included in ICMI proceedings.
The selection process is juried (curated) by committee, according to criteria such as: suitability as a demo, scientific or engineering feasibility of the proposed demo system, application, or interactivity, alignment with the conference focus, potential to engage the audience, and overall quality and presentation of the written proposal. Authors are encouraged to address such criteria in their proposals (paper submission), along with preparing the short papers mindful of the quality and rigorous scientific expectations of an ACM publication.
The curated demo program will be selected from the submitted proposals as well as invited demos from among full-length papers accepted for presentation at the conference which the committee deems suitable for demonstration.
Exhibit Submission
Exhibit proposals should be submitted following the same guidelines, formatting, and due dates as for demo proposals. The main difference is that exhibits proposals should be shorter in length (up to one page) and more suitable for very mature systems (commercial or almost commercial). Exhibits won't have a paper published in the ICMI 2017 proceedings.
All materials should be prepared in PDF format and submitted through the ICMI submission system via PCS (https://precisionconference.com/~icmi). The demo and exhibit paper submissions should not be anonymous. However, all ACM rules and guidelines related to paper submission should be followed (e.g. plagiarism, including self-plagiarism).
Important Dates
Demonstrations and Exhibits submission deadline: 29th August 2017
The 2017 International Conference on Multimodal Interaction, ICMI 2017, which will be held in Glasgow, Scotland between 13th and 17th November 2017. ICMI is the premier international forum for multidisciplinary research on multimodal human-human and human-computer interaction, interfaces, and system development. The conference focuses on theoretical and empirical foundations, component technologies, and combined multimodal processing techniques that define the field of multimodal interaction analysis, interface design, and system development. ICMI 2017 will feature a single-track main conference which includes: keynote speakers including Larry Barsalou (http://barsaloulab.org/), Danica Kragic (http://www.csc.kth.se/~danik/) and Charles Spence (https://www.psy.ox.ac.uk/research/crossmodal-research-laboratory), grand challenges, workshops, technical full and short papers, exhibits and doctoral consortium papers and demonstrations . The proceedings of ICMI'2017 will be published by ACM as part of their series of International Conference Proceedings and Digital Library.
(2017-11-16) Workshop on L2 Phonetics & Phonology of L1 Romance Learners (L2PHROL). Turin, Italy
Workshop on L2 Phonetics & Phonology of L1 Romance Learners (L2PHROL). Turin, Italy.
16-17 November 2017
The University of Turin (Laboratorio Sperimentale di Fonetics ?Arturo Genre?) and the University of Paris 8 (Laboratoire Structures Formelles du Langage) are pleased to announce that the L2PHROL workshop (L2 Phonetics and Phonology of L1 Romance Learners) will be held in Turin (Italy) on 16-17 November 2017. The L2PHROL workshop is jointly organized by universities in France and Italy and aims at bringing together researchers working on the L2 phonetics and phonology of Romance L1 learners.
Topics of the workshop:
We welcome contributions focusing on Romance L1 learners of any L2, involving any of the following 5 broad themes:
1) The acquisition of new phonological/phonetic/prosodic features in production and/or perception by speakers of a Romance L1, or by simultaneous bilinguals with at least one Romance language.
2) Common characteristics and common difficulties encountered by Romance native speakers learning an L2, such as tense-lax vowel contrasts, glottal fricative /h/, aspirated stops, stress-timed rhythm, phonological vowel length, lexical tones, prosodic realisation of contrastive focus.
3) Other phonetic characteristics of L2 speech by L1 Romance speakers.
4) The validation of phonetic/phonological theories in the light of L2 data by speakers whose L1 is a Romance language, or by simultaneous bilinguals with at least one Romance language
5) Teaching techniques or materials addressing L1 pronunciation and phonological awareness for Romance L1 learners of any L2.
Abstract submission
We invite abstracts in English (Times New Roman, 12-point font size, max. 1 page in A4 size plus optionally a second page for references and figures). Anonymous abstracts must be submitted by 1st September 2017 and will be peer-reviewed by members of the scientific committee (see http://www.lfsag.unito.it/ricerca/L2PHROL/committees.html ). More details about the submission procedure will be published on the website.
Registration Registration will open on 16th September 2017. There will be no registration fee.
(2017-11-23) Journée scientifique:Développement de l'articulation : du développement typique à la dyspraxie verbale, Grenoble, France
Appel à communication
Journée Scientifique
Développement de l?articulation : du développement typique à la dyspraxie verbale 23 novembre 2017, Grenoble
Le CRTLA-CHU Grenoble Alpes, le laboratoire LPNC, le laboratoire GIPSA-lab, et l?Association Coridys-Isère organisent 3 événements autour du développement de l?articulation de parole typique et pathologique, à destination des personnels de santé (orthophonistes, médecins, psychologues, etc.), des chercheurs et des étudiants :
Le mercredi 22 novembre 2017: un atelier sur le logiciel PHON, animé par Yvan Rose
Le jeudi 23 novembre 2017 : une journée scientifique sur les nouvelles approches théoriques, les nouveaux outils technologiques d?aide à l?identification, l?évaluation et l?intervention, ainsi que des études cliniques, avec les conférences plénières de Andrea McLeod (U. Montréal, Canada), Christelle Maillart (U. Liège, Belgique), Line Charron (U. Laval, Canada), Yvan Rose (U. Memorial Terre-Neuve, Canada)
Les 24 et 25 novembre 2017 : un ateliersur la dyspraxie verbale, animé par Line Charron (à destination du public orthophoniste)
Au cours de la journée scientifique du 23 novembre, est prévue une session posters, permettant de présenter les études récentes sur le développement typique et atypique de l'articulation chez l?enfant.
Les participants à cette journée sont invités à soumettre leur proposition de poster, sous forme d'un résumé de 500 mots, à envoyer à DyspraxieVerbale2017@chu-grenoble.fr .
La date limite de soumission est fixée au 15 juin 2017.
(2017-12-01) The 8th International Joint Conference on Natural Language Processing (IJCNLP 2017), Taipei, Taiwan
Call for Papers: The 8th International Joint Conference on Natural Language Processing (IJCNLP 2017), Taipei, Taiwan, November 27 °V December 1, 2017 (http://ijcnlp2017.org/)
The 8th International Joint Conference on Natural Language Processing (IJCNLP 2017) invites the submission of long and short papers reporting substantial, original, and unpublished research in all aspects of automated language processing. Relevant topics for the conference include, but are not limited to the following areas:
* Cognitive modeling and psycholinguistics * Dialog and interactive systems * Discourse and pragmatics * Document analysis including text categorization, topic models, and retrieval * Generation * Information extraction, text mining, and question answering * Machine learning in NLP * Machine translation and Multilinguality * Phonology, morphology, and word segmentation * Resources and evaluation * Semantics * Sentiment analysis and opinion mining * Social media * Speech * Summarization * Tagging, chunking, syntax, and parsing
Important Dates
Deadline Submission deadline for long and short papers: July 7, 2017 Author response period: August 7 - 9, 2017 Notification of acceptance: September 1, 2017 Camera ready due: September 30, 2017
** All deadlines are calculated at 11:59pm Pacific Daylight Savings Time (UTC-7).
Events Workshops, tutorials and shared tasks: November 27, 2017 and December 1, 2017 Main conference: November 28 - 30, 2017
Submission Information Paper submission for IJCNLP will be handled by the Softconf START system. The submission deadline is July 7, 2017.
Long Papers IJCNLP 2017 long paper submissions must describe substantial, original, completed and unpublished work. Wherever appropriate, concrete evaluation and analysis should be included. Each long paper submission consists of a paper of up to eight (8) pages of content, plus two pages for references; final versions of long papers will be given one additional page (up to nine pages with unlimited pages for references) so that reviewers°¶ comments can be taken into account.
Short Papers IJCNLP 2017 also solicits short papers. Short paper submissions must describe original and unpublished work. A short paper is not a shortened long paper and should have a point that can be made in a few pages. For example: * A small, focused contribution * Work in progress * A negative result * An opinion piece * An interesting application nugget
Each short paper submission consists of up to four (4) pages of content, plus 2 pages for references; final versions of short papers will be given one additional page (up to five pages in the proceedings and unlimited pages for references) so that reviewers°¶ comments can be taken into account.
Submission Format Submissions must be in PDF, and must conform to the official style guidelines in two-column format for IJCNLP 2017. We ask you to use the provided LaTeX style files (they will be posted on the conference site). Authors are strongly discouraged from modifying the style files. Please do not use other templates (e.g., Word). Submissions that do not conform to the required styles, including paper size, margin width, and font size restrictions, will be rejected without review.
As the reviewing will be blind, papers should not include the authors' names and affiliations. Furthermore, self-references that reveal the author's identity, e.g., °ßWe previously showed (Smith, 1991) ...°®, should be avoided. Instead, use citations such as °ßSmith (1991) previously showed ...°®. Acknowledgments of funding or assistance should be omitted. Submissions that do not conform to these requirements will be rejected without review. Separate author identification information is required as part of the online submission process. IJCNLP 2017 encourages the submission of supplementary material such as software and data mentioned in the paper. The supplementary material should be supplementary (rather than central) to the paper. It may include explanations or details of proofs or derivations that do not fit into the paper, lists of features or feature templates, sample inputs and outputs for a system, pseudo-code or source code, and data. It may also include reports on preprocessing decisions, model parameters, and other details necessary for the exact replication of the experiments described in the paper. The paper should be self-contained and not rely on the supplementary material. Reviewers are not asked to review or even download the supplemental material. If the pseudo-code or derivations or model specifications are an important part of the contribution, or if they are important for the reviewers to assess the technical correctness of the work, they should be a part of the main paper, not as appendices. Multiple Submission Policy Papers that have been or will be submitted to other meetings or publications must indicate this at submission time, and must be withdrawn from the other venues if accepted by IJCNLP 2017. We will not accept for publication or presentation papers that overlap significantly in content or results with papers that will be (or have been) published elsewhere. Authors submitting more than one paper to IJCNLP 2017 must ensure that submissions do not overlap significantly (>25%) with each other in content or results.
Preprint servers such as arXiv.org and workshops that do not have published proceedings are not considered archival for purposes of submission. To preserve the spirit of blind review, authors are encouraged to refrain from posting until the completion of the review process. Otherwise, authors must state in the online submission form the name of the workshop or preprint server and title of the non-archival version. The submitted version should be suitably anonymized and not contain references to the prior non-archival version. Reviewers will be told: 'The author(s) have notified us that there exists a non-archival previous version of this paper with significantly overlapping text. We have approved submission under these circumstances, but to preserve the spirit of blind review, the current submission does not reference the non-archival version.' Presentation Requirement All accepted papers must be presented at the conference to appear in the proceedings. At least one author of each accepted paper must register for IJCNLP 2017. Accepted papers will be presented orally or as a poster (at the discretion of the program chairs based on the nature rather than the quality of the work). There will be no distinction in the proceedings between papers presented orally or as posters.
(2017-12-05) International Conference On Natural Language Processing and Speech Processing , Casablanca, Morocco
First call for papers ICNLSP 2017
ICNLSP 2017 is the International Conference On Natural Language Processing and Speech Processing to be held 5-6 December, 2017, In Casablanca ? Morocco
The main goal of ICNLSP is to provide a forum for presentation, discussion and dissemination of the scientific findings in the area of Natural Language and Speech Processing. The conference welcomes papers describing original works and tool demonstration papers.
SCOPE:
Topics of either theoretical, experimental, or applied interest include, but are not limited to:
Signal processing, acoustic modeling.
Architecture of speech recognition system.
Switch code and Arabic dialects
Language processing of social network data
Deep learning for speech recognition
Speech comprehension
Speech Translation
Speech synthesis.
Speaker and language identification
Phonetics, phonology and prosody.
Cognition and natural language processing
Information retrieval on social network
Neural network language models.
Machine Learning
Text Mining
Video processing in social network
Human-Machine Dialogue
Text summarization
Invited speakers:
Jean-Paul Haton (Professor Emeritus at university of Lorraine)
Yves Lepage (Professor at University of Waseda ? Japan)
Olivier Siohan (Senior Researcher at Google ? USA)
Imed Zitouni (Senior Researcher at Microsoft ? USA)
Program Committee
Frédéric Béchet ( Professor University Aix-Marseille, France) Laurent Besacier (Professor University of Grenoble, France) Khalid Choukri (Executive director of the European Language Resources Association (ELRA)) Mona Diab (Associate Professor George Washington University) Yannick Estève (Professor University of Le Mans, France) Dominique Fohr (researcher CNRS, France) Jean-Paul Haton (Professor emeritus, University Lorraine, France) Salma Jamoussi (Assistant Professor University of Sfax, Tunisia) Denis Jouvet (Researcher INRIA Lorraine, France) David Langlois (Assistant Professor Lorraine University, France) Chiraz Latiri (Professor University of Tunis, Tunisia) Yves Lepage (Professor University Waseda, Japan) Mikolaj Leszcuk (Assistant Professor, Poland) Khalifa Mansouri (Assistant Professor University Hassan II) Odile Mella (Assistant professor at University of Lorraine) Franck Poirier (Professor University of Bretagne sud) Fatiha Sadat (Associate Professor UQAM, Canada) Khaled Shaalan (Professor The British University in Dubai, UAE) Olivier Siohan (Researcher Google, USA) Yahya Slimani (Professor University of Tunis, Tunisia) Kamel Smaili (Professor University Lorraine, France) Juan-Manual Torrès (Assistant Professor University of Avignon, France) Imed Zitouni (Researcher at Microsoft, USA)
SUBMISSIONS:
Authors are invited to submit full-length papers, with up to four pages (double column) for technical content including figures and possible references, and with one additional optional 5th page containing only references. Submissions will be done via easychair: https://easychair.org/conferences/?conf=icnlsp2017
We apologize for cross-posting and kindly ask you to forward this information to interested persons.
The DSTC shared task has now been running since 2013. This year?s challenge has been renamed to Dialog System Technology Challenge, which reflects the wider scope we aim for. The DSTC6 workshop will be co-located to one of conferences such as NIPS or IWSDS.
The challenge will include 3-4 tracks, which should reflect the interests of the community. We will ask the community to cast expressions of interest via an online voting system in order to ensure sufficient numbers of participants per track.
Submissions
-----------------
We would like to encourage you to submit a 2-page proposal (+ unlimited references, + an appendix of unlimited size containing examples of the data, annotations, and expected output to be generated), including but not limited to:
- end-to-end systems
- dialogue state tracking
- spoken language understanding
- natural language generation for SDS
- dialogue breakdown detection
- automatic evaluation metrics
- question-answering
- text to API call
Your proposal should contain:
1) The names and affiliations of the organisers;
2) A description of the task, with particular reference to its relevance for the dialog community;
3) A description of the data that will be provided for participants;
4) A description of the evaluation methods that will be used to compare peer systems;
5) An appendix of unlimited size containing examples of the data, annotations, and expected output to be generated
(2017-12-11) 9th International Conference on Intelligent Human-Computer Interaction, Evry, France
================================================================================= IHCI 2017: 9th International Conference on Intelligent Human-Computer Interaction Evry, France, December 11-13, 2017, http://ihci2017.sciencesconf.org ================================================================================= The 9th international conference on Intelligent Human Computer Interaction (IHCI 2017) will be held in Evry, near Paris, France, from 11 to 13 of December 2017.
IHCI allows researchers and practitioners to exchange on recent results in the area of human-computer interaction, related technologies (including signal processing, multimodal analysis, artificial intelligence, machine learning and cognitive modelling) and their applications. The conference will bring together researchers from academia, industry and research organizations from various disciplines, around theoretical, practical and application-oriented contributions.
This year, along with usual topics, IHCI 2017 will focus on human cognition modelling for interaction, including human cognitive process modelling (for task analysis...), human-robot interaction (for companion robots...), cognition for interaction in virtual worlds (for autonomous conversational agents...).
Keynotes will be given by : - Pr. Alain Berthoz, Honorary Professor at Collège de France, member of the French Academy of Science and Academy of Technology, on 'Simplexity and vicariance. On human cognition principles for man-machine interaction' - Pr. Mohamed Chetouani, Professor at Pierre and Marie Curie University, France, on 'Interpersonal Human-Human and Human-Robot Interactions', - Pr. Antti Oulasvirta, Associate Professor at Aalto University, Finland, on 'Can Machines Design? Optimizing User Interfaces for Human Performance'.
The IHCI topics include but are not limited to:
Human Cognition Modelling: - Cognitive models of intelligence - Modelling perceptual processes - Modelling of learning and thinking - Modelling of memory - Cognitive task analysis
User adaptation and Personalization: - Adaptive learning - Affective computing for adaptive interaction - Reinforcement learning
Machine Perception of Humans: - Speech detection and recognition - Natural language processing - Face and emotion detection - Body sensors and communication - Gesture recognition - Human motion tracking
Tactile interfaces: - Haptics fundaments - Haptic feedback for interaction - Haptic feedback for robot collaboration
Human-Robot Interaction and collaboration: - Collaborative learning - Collaborative systems - Temporal coordination modelling
Applications: - Natural User Interfaces - Human-robot interaction - Virtual and augmented reality - Remote and face-to-face collaboration - Embodied conversational agents - Mobile interfaces - Interface design for accessibility and rehabilitation - Interaction and cognition for education - Health - Serious games
--------------------------------------------------------------------------------------- **NEW:* The conference proceedings will be published as an open access volume in the Springer series Lecture Notes in Computer Science (LNCS) and indexed in the ISI Conference Proceedings Citation Index, Scopus, EI Engineering Index, Google Scholar, DBLP, etc. Papers can be either long papers (10 to 12 pages) or short papers (4 to 6 pages), and must conform to the LNCS templates (see the guidelines for authors). * --------------------------------------------------------------------------------------- Papers must be written in English and describe original work that has not been published and is not under review elsewhere. In order to enforce blind reviewing, papers must be made anonymous before submitting (by removing the author?s names and institution from the header).
Important dates: - Submission deadline: *June 30, 2017 (EXTENDED) * - Decision notification: September 10, 2017 (tentative) - Final version due: October 1st, 2017
Patrick Horain (Telecom SudParis), Chair Catherine Achard (Université Pierre et Marie Curie), Co-Chair Malik Mallem (Université Evry Val d'Essonne), Co-Chair
Since 1999 the MAVEBA Workshop aims at stimulating contacts between specialists active in bioengineering, clinical and industrial development in the area of voice signal and image analysis for biomedical applications. This tenth Workshop will offer again the participants an interdisciplinary platform for presenting and discussing new knowledge in the field of models and analysis of signal and images of the human vocal apparatus and any related field such as neurology, psychiatry, linguistics and singing. Both adult, pediatric and newborn voices are concerned. The MAVEBA Workshop welcomes contributions ranging from fundamental research to all kinds of biomedical applications and related established and advanced technologies with emphasis on translational research. Proposal for Special Sessions, sw and hw demos, round tables on specific themes are welcome.
As for past editions a book of Proceedings will be available at the time of the conference, edited by Firenze University Press. Moreover a Special Issue of an international journal included in all the major database is foreseen, collecting extended version of selected contributions presented at the MAVEBA Workshop.
I am looking forward to welcoming you again next December in Firenze and enjoy together the Florentine Christmas atmosphere!
(2017-12-14) International Workshop on Spoken Language Translation (IWSLT), Tokyo, Japan
The International Workshop on Spoken Language Translation (IWSLT) is a yearly scientific workshop, associated with an open evaluation campaign on spoken language translation, where both scientific papers and system descriptions are presented. The 14th International Workshop on Spoken Language Translation will take place in Tokyo, Japan, on December 14-15, 2017. http://workshop2017.iwslt.org/index.php
Evaluation Campaign
IWSLT 2017 will offer three official evaluation tasks: multilingual text translation of TED talks (including zero-shot translation), text translation of dialogues, speech recognition and speech translation of lectures. Multilingual translation will target English, German, Dutch, Italian and Romanian; translations of dialogues will be from Japanese to English; and speech translation of lectures will be from German to English. Additional unofficial text translations of TED talks will be offered à-la-carte according to expressions of interest by the participants. Training and development data will be released to the participants through the workshop website. For the multilingual task both large and small training data constraints will be defined.
Scientific Papers The IWSLT invites submissions of scientific papers to be published in the workshop proceedings and presented in dedicated technical sessions of the workshop, either in oral or poster form. The workshop welcomes high quality, original contributions covering theoretical and practical issues in the fields of automatic speech recognition and machine translation that are applied to spoken language translation. Possible topics include, but are not limited to:
MT and SLT approaches Integration of ASR and MT MT and SLT evaluation Language resources for MT and SLT Open source software for ASR, MT and SLT Multilingual MT and ASR Applications of MT and SLT Adaptation in MT, ASR and SLT Post- and Pre-processing for ASR, MT and SLT Efficiency in ASR, MT and SLT
IMPORTANT DATES
Evaluation Campaign
June 5: Release of train and dev data (*) Sep. 11 - 17: Multilingual task evaluation Sep. 11 - 17: Lectures ASR evaluation Sep. 18 - 24: Lectures SLT evaluation Sep. 18 - 24: Dialogue task evaluation Oct. 22: System description paper Nov. 12: Review feedback Nov. 26: Camera ready (*) Release of training data of the Dialogue task will be announced later.
Scientific Papers
Sep. 30: Paper submissions Oct. 31: Notification of acceptance Nov. 12: Camera ready
Submitted manuscripts will be subject to a blind peer-reviewed. Authors of accepted papers are requested to present their paper at the workshop.
(2017-12-16)CfP IEEE Automatic Speech Recognition and Understanding Workshop, Okinawa, Japan
ASRU 2017 IEEE Automatic Speech Recognition and Understanding Workshop December 16-20, 2017 Okinawa, Japan http://asru2017.org CALL FOR PAPERS The biennial IEEE ASRU workshop has a tradition of bringing together researchers from academia and industry in an intimate and collegial setting to discuss problems of common interest in automatic speech recognition, understanding, and related fields of research. The workshop includes keynotes, invited talks, poster sessions and will also feature challenge tasks, panel discussions, and demo sessions. TOPICS AND FOCUS We invite papers in all areas of spoken language processing, with emphasis placed on the following topics: - Automatic speech recognition (ASR) - ASR in adverse environments - New applications of ASR - Speech-to-speech translation - Spoken document retrieval - Multilingual language processing - Spoken language understanding - Spoken dialog systems - Text-to-speech systems VENUE The ASRU workshop will take place in Okinawa, Japan. Okinawa is a subtropical island located roughly 640 kilometers (400 mi) south of the main islands of Japan. It is one of Japanfs main tourist destinations because of its warm weather, its rich natural resources, and its unique blend of cultures that evolved through centuries of trade with China, Korea and other Southeast Asian countries. FORMAT The workshop features one keynote and one or two invited talks a day. Regular papers are presented as posters. ASRU 2017 will also include challenge tasks, panel discussions and demo sessions. SCHEDULE Paper Submission............. June 29, 2017 Paper Notification........... August 31, 2017 Early Registration Period:... August 31 - Oct 5, 2017 Camera Ready Deadline........ Sept 21, 2017 Workshop..................... Dec 16-20, 2017 MORE INFORMATION For updates see http://www.asru2017.org
The INTERNATIONAL WORKSHOP ON SPOKEN DIALOGUE SYSTEMS TECHNOLOGY (IWSDS) 2018 invites proposals for Workshops and Special Sessions in any topic related to the main conference theme: 'Towards creating more human-like conversational agent technologies.'
Authors are requested to submit PDF files (maximum three pages) of their proposal to the following email: iwsds2018@gmail.com
The proposal must indicate:
1. Whether the proposal is for a workshop or for a special session:
Workshops are half day events collocated either before or after the IWSDS 2018 main program. Registration to workshops is not included with IWSDS registration. Participants only interested in attending the workshops do not need to register for IWSDS.
Special sessions are 90-minute sessions that are part of the IWSDS main program. Registration to special sessions is included with IWSDS registration.
2. Workshop / Special Session title
3. Name, affiliation, e-mail and phone number of the organizers
4. Tentative program committee members (only for workshop proposals)
5. A description of the workshop / Special Session including:
Objectives
Topics of interest
Justification
Expected number submissions
Tentative program
6. Special audio-visual, internet, computer or equipment requirements
7. Whether the workshop / special session have been run before:
- Where and when
- Number of participants
8. Any additional information that might be relevant for the proposal evaluation
Proposal submission deadline: August 15, 2017
Proposal submission notification: September 1, 2017
Important notice:
Based on the volume of submissions and other logistic constrains, accepted workshops can be converted into special sessions or vice versa.
IWSDS 2018 organization will not provide any kind of financial support to workshop and special session organizers. IWSDS 2018 organization will only cover expenses related to venue, audio-visual equipment and coffee breaks for workshops and special sessions.
The INTERNATIONAL WORKSHOP ON SPOKEN DIALOGUE SYSTEMS TECHNOLOGY (IWSDS) 2018 invites paper submissions especially on the following topics:
Engagement and emotion in human-robot interactions
Digital resources for interactive applications
Multi-modal and machine learning methods
Companions, personal assistants and dialogue systems
Proactive and anticipatory interactions
Educational and healthcare robot applications
Dialogue systems and reasoning
Big data and large scale spoken dialogue systems
Multi-lingual dialog systems
Spoken dialog systems for low-resource languages
Domain Transfer and adaptation techniques for spoken dialog systems
However, submissions are not limited to these topics, and submission of papers in all areas of spoken dialogue systems is encouraged. We particularly welcome papers that can be illustrated by a demonstration, and will organize the conference in order to best accommodate these papers, whatever their category.
As in previous years, a selection of accepted papers will be published in a book by Springer following the conference (Springer LNEE series, SCOPUS and other important indexes).
Authors are requested to submit PDF files of their manuscripts using the paper submission system (https://easychair.org/conferences/?conf=iwsds2018)
We distinguish between the following categories of submissions:
Long Research Papers are reserved for reports on mature research results. The expected length of a long paper should be in the range of 8-12 pages, including references.
Short Research Papers should be in the range of 4-6 pages, including references. Authors may choose this category if they wish to report on smaller case studies or ongoing but interesting and original research efforts.
Position Papers deal with novel research ideas or view-points which describe trends or fruitful starting points for future research and elicit discussion and are not much researched. They should be 2 pages long, excluding references.
Demo Submissions - System Papers: Authors who wish to demonstrate their system may choose this category and provide a description of their system and demo. System papers should not exceed 6 pages in total.
IWSDS 2018 requires that all authors wishing to present a paper take into account:
The paper is substantially original and will not be submitted to any other conference or journal during the IWSDS 2018 review period.
The paper does not contain any plagiarism.
The paper will be presented by one of the authors in-person at the conference site according to the schedule published. Any paper accepted in the technical program, but not presented on-site will be withdrawn from the official conference proceedings.
Paper submission deadline: November 30, 2017
Paper notification deadline: December 29, 2017
Templates for formatting are available at:
Latex Style and Template: http://workshop.colips.org/iwsds2018/resources/svmult.zip
Word Template: http://workshop.colips.org/iwsds2018/resources/T1-book.zip
Requirements for submitting figures that are acceptable: http://workshop.colips.org/iwsds2018/resources/Art_Guidelines.pdf
The program for ICASSP 2018 will include Special Sessions that complement the traditional program with new and emerging topics of interest to the signal-processing community, particularly those that are in line with the theme of the conference. The aim of a special session is to provide an overview of the state-of-the-art as well as to highlight current research directions and challenges in specific fields of signal processing.
Prospective organizers of Special Sessions should submit proposals indicating:
+ Title of the Special Session + Motivation, indicating the novelty of the topic and why it is timely. + Short biography of the organizers + List of six (6) contributed papers (including titles, authors, contact information of the corresponding author, and a short abstract of each contribution). Each organizer may not contribute more than one paper, and organizers should contact the authors of contributed papers and secure their participation prior to submission of the proposal.
Only a maximum of three organizers per Special Session is allowed.
Proposals will be evaluated based on the timeliness and attractiveness of the topic as well as on the qualifications of the organizers and the authors of the contributed papers.
Special session proposals are due by August 4, 2017, and notification of accepted proposals will be on September 8, 2017. Just as with regular conference papers, five page papers for approved Special Sessions must be submitted by October 27, 2017.
The papers in each accepted Special Session will undergo a review process identical to that of regular papers. It is the responsibility of the organizers to ensure that their Special-Session papers meet ICASSP quality standards. In case a paper in a Special Session does not meet the expected quality, it will be rejected, and an effort will be made to draw papers from the regular-submission process to fill the gap. If too few papers for a given Special Session are accepted in the review process, and we are unable to find suitable substitutes from the regular review pool, the Special Session may be canceled?in such a case, the accepted papers from a canceled Special Session will be placed into the regular program.
The European Language Resource Association (ELRA) is glad to announce the 11th edition of LREC, organised with the support of international organisations ? many from Asia: the Asian Federation of Natural Language Processing (AFNLP), Oriental COCOSDA, the Association of Natural Language Processing - Japan, the Chinese Information Processing Society of China, the Linguistic Data Consortium, the Artificial Intelligence Association of Thailand, the Korean Society for Language and Information, the Korean Special Interest Group of Human and Cognitive Language Technology, ...
CONFERENCE AIMS LREC is the major event on Language Resources (LRs) and Evaluation for Human Language Technologies (HLT). LREC aims to provide an overview of the state-of-the-art, explore new R&D directions and emerging trends, exchange information regarding LRs and their applications, evaluation methodologies and tools, communicate on-going and planned activities, identify industrial uses and needs, and address requirements from e-science and e-society, with respect to scientific, technology, policy and organisational issues.
For this edition, which celebrates its 20th anniversary, LREC goes East in order to support a stronger interaction and synergy with the Asian NLP community and to help promoting Asian Language Resources and Language Technologies.
LREC provides a unique forum for researchers, industrials and funding agencies from a wide spectrum of related disciplines to discuss issues and opportunities, find new synergies and promote initiatives for international cooperation, in support of investigations in language sciences, progress in language technologies (LTs) and development of corresponding products, services and applications, and standards.
CONFERENCE TOPICS Issues in the design, construction and use of LRs: text, speech, sign, gesture, image, in single or multimodal/multimedia data * Guidelines, standards, best practices and models for LRs interoperability * Methodologies and tools for LRs construction and annotation * Methodologies and tools for extraction and acquisition of knowledge * Ontologies, terminology and knowledge representation * LRs and Semantic Web * LRs and Crowdsourcing * Metadata for LRs and semantic/content mark-up
Exploitation of LRs in systems and applications * Sign language, multimedia information and multimodal communication * LRs in systems and applications such as: information extraction, information retrieval, audio-visual and multimedia search, speech dictation, meeting transcription, Computer Aided Language Learning, training and education, mobile communication, machine translation, speech translation, summarisation, web services, semantic search, text mining, inferencing, reasoning, sentiment analysis/opinion mining, etc. * Interfaces: (speech-based) dialogue systems, natural language and multimodal/multisensory interactions, voice-activated services, etc. * Use of (multilingual) LRs in various fields of application like e-government, e-participation, e-culture, e-health, mobile applications, digital humanities, social sciences, etc. * Industrial LRs requirements * User needs, LT for accessibility
Issues in LT evaluation * LT evaluation methodologies, protocols and measures * Validation and quality assurance of LRs * Benchmarking of systems and products * Usability evaluation of HLT-based user interfaces and dialogue systems * User satisfaction evaluation
General issues regarding LRs & Evaluation * International and national activities, projects and initiatives * Priorities, perspectives, strategies in national and international policies for LRs * Multilingual issues, language coverage and diversity, less-resourced languages * Open, linked and shared data and tools, open and collaborative architectures * Replicability and reproducibility issues * Organisational, economical, ethical and legal issues
LREC 2018 HOT TOPICS
Asian Language Resources Special attention will be devoted to highlight the wide variety of initiatives for the creation, use and evaluation of Asian Language Resources and Technologies. Special attention will be paid to Less-Resourced Languages in the Asian area, including (local) Sign Languages.
International Contribution to Olympics 2020 LREC 2018 would like to promote all LTs that would support better interactions and communications between the Olympics 2020 visitors and the local hosts. This involves all speech- and text-based computer interactions, speech/sign to speech/sign translations, human-human communications mediated by computers, etc. Assessment of the above mentioned technologies is also an important area within LREC 2018.
Language Resources in the Online World In a time in which more and more (language) data are generated, either by human beings or by machines, and directly streamed, the question arises how LRs and LTs can cope with this development. A first challenge is to address and to provide for correctives to hate speeches, cyberbullying, fake news, etc. Can LT provide means to process and respond in a timely manner to such language data streamed in a huge amount at high speed? In this context, language technologists have to intensify cooperation with humanities, especially social and political sciences, psychology but also economics, and more.
DESCRIBE AND SHARE YOUR LRs! In addition to describing your LRs in the LRE Map ? now a normal step in the submission procedure of many conferences ? LREC recognises the importance of sharing resources and making them available to the community. When submitting a paper, you will be offered the possibility to share your LRs (data, tools, web-services, etc.), uploading them in a special LREC repository set up by ELRA. Your LRs will be made available to all LREC participants before the conference, to be re-used, compared, analysed. This effort of sharing LRs, linked to the LRE Map for their description, contributes to creating a common repository where everyone can deposit and share data.
PROGRAMME The Scientific Programme will include invited talks, oral presentations, poster and demo presentations, and panels, in addition to a keynote address by the winner of the Antonio Zampolli Prize. We will also organise an Industrial Track.
Submission of extended abstracts for oral and poster (or poster+demo) papers: 25 September 2017
LREC 2018 asks for a 3 to 4 pages (references excluded) extended abstract which must strictly follow the LREC stylesheet. Extended abstracts must be submitted through START @ https://www.softconf.com/lrec2018/main/ and will be peer-reviewed. Submissions are NOT anonymous.
Submission of proposals for panels, workshops and tutorials: 25 September 2017
PROCEEDINGS The Proceedings will include both oral and poster papers, in the same format. Final papers will range from 4 to 8 pages, with no difference in quality between shorter and longer submissions. There is also no difference in quality between oral and poster presentations. Only the appropriateness of the type of communication (more or less interactive) to the content of the paper will be considered. The importance of LREC in Natural Language Processing is reflected by the H5-Index citation ranking in Google Scholar: LREC is ranked 3rd among Computational Linguistics conferences. In addition, since 2010, LREC Proceedings are included in the Thomson Reuters Conference Proceedings Citation Index.
CONFERENCE PROGRAMME COMMITTEE Nicoletta Calzolari ? CNR, Istituto di Linguistica Computazionale ?Antonio Zampolli?, Pisa - Italy (Conference chair) Khalid Choukri ? ELRA, Paris - France Christopher Cieri ? Linguistic Data Consortium, Philadelphia - USA Thierry Declerck ? DFKI GmbH, Saarbrücken - Germany Koiti Hasida ? The University of Tokyo, Tokyo - Japan Hitoshi Isahara ? Toyohashi University of Technology, Toyohashi - Japan Bente Maegaard ? Centre for Language Technology, University of Copenhagen, Copenhagen - Denmark Joseph Mariani ? LIMSI-CNRS, Orsay - France Asuncion Moreno ? Universitat Politècnica de Catalunya, Barcelona - Spain Jan Odijk ? UIL-OTS, Utrecht - The Netherlands Stelios Piperidis ? Athena Research Center/ILSP, Athens - Greece Takenobu Tokunaga ? Tokyo Institute of Technology, Tokyo ? Japan
CONFERENCE EDITORIAL COMMITTEE Sara Goggi, CNR, Istituto di Linguistica Computazionale ?Antonio Zampolli?, Pisa, Italy Hélène Mazo, ELDA/ELRA, Paris, France
