(2016-05-09) 5th Workshop on Spoken Language Technologies for Under-Resourced Languages (SLTU'16), Yogyakarta, Indonesia.
Technologies for Under-Resourced Languages (SLTU'16)5th Workshop on Spoken Language Technologies for Under-Resourced Languages (SLTU'16) will be held on 9-12 May 2016 in Yogyakarta, Indonesia.
### Important dates ### - Full paper submission: 25 January 2016 - Notification of acceptance: 07 March, 2016 - Submission of final papers: 21 March, 2016 - Early registration: 21 March, 2016 - Workshop dates: 9-12 May, 2016
The Workshop on Spoken Language Technologies for Under-Resourced Languages is the fifth in a series of even-year SLTU Workshops. Four previous Workshops were organized: SLTU'14 in St. Petersburg (Russia), SLTU'12 in Cape Town (South Africa), SLTU'10 in Penang (Malaysia), and SLTU'08 in Hanoi (Vietnam). SLTU?16 is held in Yogyakarta (Indonesia), a centre of classical Javanese culture. There are more than 700 ethnic languages spoken in Indonesian archipelago, but 146 are endangered. Therefore, SLTU?16 has special focus on under-resourced languages and endangered languages, but other related topics are also encouraged.
SLTU?16 will continue the tradition of previous SLTUs that features a number of distinguished keynote speaker, and this year, for the first time, SLTU will also offer Kaldi Tutorial on Under-Resourced Language.
### Workshop Topics ### Areas related to processing any under-resourced and endangered languages: - Fast resources acquisition (text and speech corpora, parallel text, dictionary, grammars, language model) - Spoken language processing for language without dictionary or written forms - Cross-lingual and multi-lingual spoken language processing including analysis and synthesis - Speech recognition and synthesis of low-resourced languages and dialects - Machine translation and spoken dialogue systems - Applications of spoken language technologies for under-resourced languages
### Paper submission ### Prospective authors are invited to submit full-length papers up to 4 pages for technical content (including figures, tables, etc) and possible references, plus one additional (optional) page containing only references.
### Important dates ### - Full paper submission: 25 January 2016 - Notification of acceptance: 07 March, 2016 - Submission of final papers: 21 March, 2016 - Early registration: 21 March, 2016 - Workshop dates: 9-12 May, 2016
Framing speech: Celebrating 40 years of inquiry with Stefanie Shattuck-Hufnagel
We are pleased to announce a satellite meeting to the Speech Prosody 2016 conference in Boston, the purpose of which is to celebrate Stefanie Shattuck-Hufnagel?s 40 years of work in our field. The satellite meeting will be held the afternoon of June 3, 2016, after the close of Speech Prosody. We are now opening submissions for either paper or poster presentations at this event. Papers addressing questions related to any of the many areas Stefanie has enjoyed discussing and investigating over the years are equally welcome. Papers need not directly address Stefanie?s own work. A partial list of subject areas, in no particular order, might include: speech errors, planning, disfluencies, intonation analysis and transcription, rhythm, gesture, voice quality, features and cues.
Anyone wishing to present at this meeting should submit a one page abstract (with a second page optional for figures, examples, and references) by March 1. More details on submission instructions can be found here:http://sites.bu.edu/speechprosody2016/satellite-meeting-framing-speech/
(2016-05-31) Speech Prosody 2016, Boston University, MA, USA
Speech Prosody 2016, the eighth international conference on speech prosody, will be hosted at Boston University, May 31 to June 3, 2016. We invite papers addressing any aspect of the science and technology of prosody. This year, we especially invite submissions concentrating on variation and differences both at the level of the community and that of the individual. Speech Prosody, the biennial meeting of the Speech Prosody Special Interest Group (SProSIG) <http://speechprosody2010.illinois.edu/sprosig.php> of the International Speech Communication Association (ISCA) <http://www.isca-speech.org/>, is the only recurring international conference focused on prosody as an organizing principle for the social, psychological, linguistic, and technological aspects of spoken language. Past conferences in Aix-en-Provence, Nara, Dresden, Campinas, Chicago, Shanghai and Dublin have each attracted 300-400 delegates, including experts in the fields of Linguistics, Computer Science, Electrical Engineering, Speech and Hearing Science, Psychology, and related disciplines.
Keynote Speakers for Speech Prosody 2016, Boston:
Aoju Chen, Universiteit Utrecht Laura Dilley, Michigan State University Rupal Patel, Northeastern University Patrick Wong, Chinese University of Hong Kong
We are pleased to announce the special sessions of Speech Prosody 2016:
? Rising intonation in English and beyond (Organizers: Meghan Armstrong, Page Piccinini, Amanda Ritchart) ? Sentence-final particles and intonation: Similarities, interactions, and historical relationships (Organizers: James Sneed German, K. K. Luke) ? Sources of Prosodic Variation across Recording Settings: Measures before measuring speech signals from inside and outside the lab (Organizers: Oliver Niebuhr, Petra Wagner) ? Speaker comfort and communication in noisy environments (Special Poster Session) (Organizers: Oliver Niebuhr, Simone Graetzer)
*Important Deadlines*
- Submission of Papers: November 15, 2015 - Notification of Acceptance (by email): January 15, 2016 - Early Registration Deadline: February 15, 2016 - Author's Registration Deadline: March 1, 2016 - Conference: May 31 - June 3, 2016
1. Phonology and phonetics of prosody 2. Signal processing 3. Rhythm and timing 4. Prosody in computational linguistics 5. Acquisition of first language prosody 6. Syntax, semantics, and pragmatics 7. Prosody in language and music 8. Prosody in Tone Languages 9. Prosody in language contact and second language acquisition 10. Prosody of under-resourced languages and dialects 11. Audiovisual prosody modeling and analysis 12. Communicative situation and speaking style 13. Prosodic aspects of speech and language pathology 14. Psycholinguistic, cognitive, neural correlates of prosody 15. Meta-linguistic and para-linguistic communication 16. Voice quality, phonation, and vocal dynamics 17. Prosody of sign language 18. Prosody in automatic speech synthesis, recognition and understanding
The goal of this special issue is to highlight the current state of research efforts on speaker and language recognition andcharacterization. New ideas about features, models, tasks, datasetsorbenchmarks are growing, making this a particularly exciting time.Topics of interest include, but are not limited to, those of Odyssey 2016 (follow the link above for more details).
Guest Editors: Eduardo LleidaUniversity of Zaragoza, Spain Luis J. RodrÃguez-FuentesUniversity of the Basque Country, Spain
Important dates (tentative): Submission open:April 11, 2016 Submission deadline:July 22, 2016 Notifications of final decision:February 23, 2017 Scheduled publication:March, 2017
Though the call for papers to this special issue is open, authors with best reviews at Odyssey 2016 will be invited to submit extended versions of their papers (at least 30% of the material must be new). Note that CSL papers have no page limit. All papers will go through the same rigorous review process as regular CSL papers, with a minimum of two reviewers per paper.
*DEADLINES EXTENDED !!! (no further extensions will be done)*
Regular paper submissions February 5, 2016 Show & Tell / Industry & Forensics February 22, 2016 Notifications March 22, 2016 Camera ready papers April 8, 2016
*NEW !!!* *A _Special Issue_of _Computer Speech and Language_is under* *consideration (see details below). If approved, there will be* *an open call, and authors with best reviews at Odyssey 2016* *will be invited to submit extended versions of their papers.*
The general themes of the workshop include speaker and language recognition and characterization. The specific topics include, but are not limited to, the following:
o Speaker and language recognition, verification, identification o Speaker and language characterization o Features for speaker and language recognition o Speaker and language clustering o Multispeaker segmentation, detection, and diarization o Language, dialect, and accent recognition o Robustness in channels and environment o System calibration and fusion o Speaker recognition with speech recognition o Multimodal speaker recognition o Speaker recognition in multimedia content o Machine learning for speaker and language recognition o Confidence estimation for speaker and language recognition o Corpora and tools for system development and evaluation o Low-resource (lightly supervised) speaker and language recognition o Speaker synthesis and transformation o Human and human-assisted recognition of speaker and language o Spoofing and tampering attacks: analysis and countermeasures o Forensic and investigative speaker recognition o Systems and applications
------------------------------------------------------------------------ *WORKSHOP FORMAT AND PAPER SUBMISSION*
As in previous editions <http://www.speakerodyssey.com>, Odyssey 2016 will consist of plenary oral and poster sessions, with special sessions on topics of interest, Show & Tell (demo) sessions and panel discussions with industry partners.
Regular papers (including those for special sessions) and Show & Tell papers must be uploaded in PDF format to the Odyssey 2016 Submission System:
Regular papers (including those for special sessions) must be at most 8 pages long and are expected to include scientific or methodological novelty, which must be stated clearly in the Introduction, along with a review of the relevant prior work. Each paper will be reviewed by at least three members of the scientific committee. Accepted papers will appear in electronic proceedings, and will be accessible through the ISCA Archive < http://www.isca-speech.org/iscaweb/index.php/archive/online-archive>.
For the Show & Tell (demo) sessions, authors must submit short papers (at most, 4 pages long) describing a system or prototype, a target application, a product, a demonstrator or any combination of them. These contributions do not have to present scientific or methodological novelty; therefore, they will not undergo full peer review and will not be included in the proceedings (though will be available for download on the website). One or more poster sessions will be allocated for Show & Tell submissions, with auxiliary equipment (tables, plugs, etc.) available if requested. The organizing committee may select the most interesting submissions for oral presentation.
------------------------------------------------------------------------ *INDUSTRY AND FORENSICS TRACK*
To foster a closer collaboration across industry and academia, an industry track was introduced in Odyssey 2014. The initiative is continued in Odyssey 2016 under the name 'Industry and Forensics track', in order to include forensic and investigative speaker recognition, an application which involves diverse areas of expertise. Companies, R&D labs, government agencies and other interested parties (e.g. forensic experts and labs) are called to participate in the following sessions:
*- Forensic and investigative speaker recognition* *- Commercial applications of speaker and language recognition*
These sessions are expected to be highly interactive, with a series of pitch talks (3-5 minutes long each), followed by a panel discussion open to the audience, addressing practical issues or unsolved problems 'out-in-the-wild' that deserve attention.
To participate, just send an email to info@odyssey2016.org < mailto:info@odyssey2016.org> with 'Industry and Forensics track' as Subject, providing details of your company profile (in particular, your involvement with or your need for speaker and language recognition technology), your interests (forensics, commercial or other) and contact info. Besides voice biometrics providers and companies that develop and exploit speaker/language recognition solutions, we encourage companies who are IN NEED for speaker or language recognition technology to participatre in these sessions.
------------------------------------------------------------------------ *SPECIAL SESSION 1: Speaker Recognition in Multimedia Content (SS-SRMC)*
Speaker information is instrumental in better exploiting spoken multimedia content, as evidenced by recent work on large-scale speaker indexing and linking, or on speaker naming in broadcast archives.
The special session 'Speaker recognition in multimedia content', organized in collaboration with the ISCA SIG on Speech and Language in Multimedia (SIG-SLIM, http://slim-sig.irisa.fr/), pursues two main goals: (1) to share recent advances in the field and to identify synergies between the various multimedia applications where speaker recognition, indexing and segmentation is considered; and (2) to raise awareness on speaker-related research in multimedia so as to strengthen the link between the multimedia and the speaker recognition communities.
The session targets researchers working on any topic related to speaker characterization for multimedia content processing, including (but not limited to) speaker segmentation, speaker indexing, speaker clustering, speaker naming or discovery, or speaking face detection. Multimodal (e.g. speech + face recognition) approaches are particularly welcome. We expect submissions presenting original research results, ongoing research and development projects, tools and resources that are being made available, or benchmarking initiatives.
Submissions to this Special Session must be done under the topic:
In 2015 NIST launched a Language Recognition i-Vector Machine Learning Challenge as an alternative evaluation methodology to attract newcomers to the field by reducing the effort required to preprocess the data through the use of i-vectors.
This special session focuses on the recent advances in language recognition in the context of the NIST Challenge as well as on the Challenge results. As such, we invite participants of the Challenge as well as researchers who work on the language recognition task using i-vectors to submit papers about their systems or techniques. Novel uses of i-vectors for language recognition as well as data resources and benchmark results are of special interest.
Submissions to this Special Session are expected to present original ideas or results, and must be done under the topic:
'Machine learning for speaker and language recognition'
*- A best paper award* *- A best student paper award*
All regular papers (including special session papers) are candidates for the awards. The awards are given based on the review reports AND the presentation at the conference. For the best student paper award, the first author must be a student (meaning that she/he does not yet hold a PhD degree) at the time of paper submission.
Luis J. RodrÃguez-Fuentes, chair University of the Basque Country, Spain Eduardo Lleida, co-chair University of Zaragoza, Spain Jean-François Bonastre University of Avignon, France Niko Brümmer Agnitio, South Africa Lukáš Burget Brno University of Technology, Czech Republic Joseph Campbell MIT Lincoln Laboratory, USA Jan 'Honza' ÄŒernocký Brno University of Technology, Czech Republic Tomi Kinnunen University of Eastern Finland, Finland Haizhou Li Institute for Infocomm Research, Singapore Alvin Martin NIST, USA Douglas Reynolds MIT Lincoln Laboratory, USA
------------------------------------------------------------------------ *COMPUTER SPEECH AND LANGUAGE -- Special Issue (AWAITING APPROVAL)*
'Recent advances in speaker and language recognition and characterization'
The goal of this special issue is to highlight the current state of research efforts on speaker and language recognition and characterization. New ideas about features, models, tasks, datasets or benchmarks are growing, making this a particularly exciting time. Topics of interest include, but are not limited to, those of Odyssey 2016 (as listed above). Guest Editors:
Eduardo Lleida University of Zaragoza, Spain Luis J. RodrÃguez-Fuentes University of the Basque Country, Spain
Important dates (tentative):
Submission deadline July 22, 2016 Notifications December 23, 2016 Scheduled publication March, 2017
Though the call for papers to this special issue is open, authors with best reviews at Odyssey 2016 will be invited to submit extended versions of their papers (at least 30% of the material must be new). Note that CSL papers have no page limit. All papers will go through the same rigorous review process as regular CSL papers, with a minimum of two reviewers per paper.
------------------------------------------------------------------------ *VENUE AND TRAVEL*
Odyssey 2016 will be hosted by two Spanish groups: GTTS (http://gtts.ehu.es), from the Faculty of Science and Technology of the University of the Basque Country, and ViVoLab (http://vivolab.unizar.es/), from the School of Engineering and Architecture of the University of Zaragoza.
The workshop will be held in Bilbao < http://www.bilbaoturismo.net/BilbaoTurismo/en/tourists>, a medium-size city in the north of Spain, with about 350,000 inhabitants. The venue, Bizkaia Aretoa < http://www.ehu.eus/en/web/bizkaia-aretoa/home>, is located in the heart of the city. The building, designed by the Portuguese architect Alvaro Siza, hosts all kind of social, cultural, academic and scientific events, most of them organized by the University of the Basque Country.
Bilbao is the commercial and administrative head of a large area of about one million people living by the Ibaizabal-Nervion estuary. After centuries of trading and iron industry, in the last decades Bilbao has become a service town, supported by a huge investment in infrastructure and urban renewal, that started with the construction of an underground network (Metro Bilbao) in 1995 and the opening of the Bilbao Guggenheim Museum in 1997.
The Bilbao airport < http://www.aena.es/csee/Satellite/Aeropuerto-Bilbao/en/Home.html> can be easily reached from many European airports, including international hubs such as Amsterdam, Brussels, Frankfurt, Istanbul, London, Madrid or Paris, which provide worldwide connectivity. The city is connected to the European road network by the AP-8 toll motorway, to the north of Spain by the A-8 (free) motorway and to the rest of Spain by the AP-68 toll motorway.
Located in a hilly countryside, Bilbao offers many outdoor activities. Hiking is very popular as well as rock climbing in the nearby mountains. Mount Artxanda, easily accessible from the town centre by a funicular railway, features a recreational area at the summit, with restaurants, a sports complex and a balcony with panoramic views. In the south, the natural wonders of Mount Pagasarri receive hundreds of hikers every weekend.
A few minutes away by public transport, the Bizkaia Bridge, declared World Heritage in 2006, connects Portugalete and Las Arenas at the left and right banks of the estuary. In the coast, old fishing villages like Plentzia, Mundaka or Lekeitio have become touristic spots due to the nearby beaches, where watersports, especially surfing, are practiced. Just an hour away by car, the beautiful city of San Sebastian, as well as the vineyards and wineries of La Rioja, are worth a visit.
------------------------------------------------------------------------ *For more details:*
------------------------------------------------------------------------ *Odyssey 2016 is supported by:*
- ISCA SIG-SpLC - University of the Basque Country - University of Zaragoza - Spanish Thematic Network on Speech Technology - AGNITIO VOICE ID - CIRRUS LOGIC ------------------------------------------------------------------------
Articles RÉCITAL (12 pages plus 2 pages maximum pour les références) Date limite de soumission : 29 mars 2016 (23:59 heure Paris) Notification aux auteurs : 10 mai 2016 Date limite de soumission des versions définitives : 23 mai 2016
** Présentation générale **
Les laboratoires franciliens travaillant dans les domaines de la parole et du traitement automatique des langues écrites, parlées et signées organisent la cinquième édition conjointe de la conférence JEP-TALN-RECITAL qui aura lieu
du 4 au 8 juillet 2016
dans les locaux de l'INalCO (13ème arrondissement de Paris).
Pour la cinquième fois, après Nancy en 2002, Fès en 2004, Avignon en 2008 et Grenoble en 2012, l'AFCP (Association Francophone pour la Communication Parlée) et l'ATALA (Association pour le Traitement Automatique des Langues) organisent conjointement leur principale conférence afin de réunir en un seul lieu les deux communautés de l'analyse et du traitement des langues écrites, parlées et signées.
Cette édition regroupera donc : - les 31e Journées d'Etudes sur la Parole (JEP), - la 23e conférence sur le Traitement Automatique des Langues Naturelles (TALN), - la 18e Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL).
RECITAL 2016, la conférence annuelle des jeunes chercheurs associée à TALN, offre aux jeunes chercheurs en Traitement Automatique des Langues (TAL) l'occasion de présenter leurs travaux et de comparer leurs approches. Elle est réservée aux étudiants (master et doctorat) et aux jeunes chercheurs ayant obtenu leur doctorat depuis moins d'un an.
Fort du succès des années précédentes, nous encourageons la soumission de travaux même préliminaires, de projets de thèse, et de travaux des premiers mois de recherche (état de l'art, premières pistes, etc.). L'objectif premier de RECITAL est de soutenir les travaux des jeunes chercheurs en TAL, de leur apporter de la visibilité et de faciliter leur intégration dans notre communauté. À ce titre, nous visons :
- des relectures pédagogiques : les auteurs doivent pouvoir comprendre les erreurs qu'ils ont pu commettre afin de pouvoir les corriger et améliorer la qualité de leur travail ;
- des relectures positives : les retours aux jeunes chercheurs sont faits dans une perspective constructive, afin d'encourager/guider les travaux, à la fois pour reconnaître leur potentiel ou pour prévenir de possibles difficultés à venir ;
- l'échange direct : les relectures seront communiquées signées, donc non-anonymes, aux auteurs. Libre à eux (ou mieux, aux relecteurs) d'aller informellement discuter ensemble lors de la conférence.
Cet appel offre l'opportunité, pour de jeunes chercheurs, de faire connaître leurs idées et travaux en cours et d'obtenir des avis de la communauté scientifique, autant lors du processus de relecture que, pour les articles acceptés, lors de leur présentation pendant la conférence.
Le prix du meilleur article RECITAL sera décerné lors de la cérémonie de clôture.
La langue officielle de la conférence est le français. Les communications en anglais sont acceptées pour les participants non francophones.
** Thématiques *
Les communications pourront porter sur tous les thèmes habituels du TAL, incluant, de façon non limitative :
- Phonétique, phonologie, morphologie, étiquetage morphosyntaxique - Syntaxe, grammaires, analyse syntaxique, chunking - Sémantique, Pragmatique, Discours, - Sémantique lexicale et distributionnelle, - Aspects linguistiques et psycholinguistiques du TAL, - Ressources pour le TAL, - Méthodes d'évaluation pour le TAL, - Applications du TAL (recherche et extraction d'information, question-réponse, génération et résumé, dialogue, analyse d'opinions, etc.), - TAL et interface multi-modale (parole, vision, etc.), - TAL et multilinguisme, - TAL pour le Web et les réseaux sociaux, - TAL et langues peu dotées, - TAL et langue des signes, - TAL et éthique.
** Types de communications **
Les auteurs sont invités à proposer deux types de communications : - des articles présentant des travaux de recherche originaux, - des prises de position présentant un point de vue sur l'état des recherches en TAL.
Les soumissions en anglais sont acceptées dès lors qu'un co-?auteur n'est pas francophone. Les articles sélectionnés seront publiés dans les actes de la conférence.
Les travaux devront présenter des contributions non publiées dans d?autres conférences. Ainsi, les traductions d?articles déjà publiés ne seront pas acceptées.
** Critères de sélection **
Les auteurs doivent être des étudiant(e)s ou bien des jeunes docteur(e)s ayant soutenu leur thèse depuis moins d'un an. Les publications avec des chercheurs confirmés (ce qui inclut les directeurs de thèses) doivent être soumises à TALN et non à RECITAL. La double soumission à RECITAL et TALN n?est pas autorisée.
Les auteurs sont invités à soumettre des travaux de recherche originaux, n'ayant pas fait l'objet de publications antérieures. Les soumissions seront examinées par au moins deux spécialistes du domaine. Seront considérées en particulier : - la correction du contenu scientifique et technique - la situation des travaux dans le contexte de la recherche internationale - l'organisation et la clarté de la présentation - l'adéquation aux thèmes de la conférence
Les articles sélectionnés seront publiés dans les actes de la conférence. Suivant l'avis du comité de programme, les présentations se feront soit sous forme orale soit sous forme de poster.
** Modalités de soumission **
Les soumissions doivent être conformes aux lignes directrices de style officielles qui sont contenues dans les fichiers de style et doivent être en format PDF. Les relectures sont signées pour permettre un échange supplémentaire plus approfondi mais le processus de relecture reste en aveugle, ce qui signifie que les contributions ne doivent inclure ni les noms ni les affiliations des auteurs. En outre, les auto-références et les noms de projets qui révèlent l?identité des auteurs, comme par exemple, « Nous avons déjà démontré (Martin, 1991) » doivent être évitées. Les auteurs devront ainsi privilégier les citations telles que « Martin a précédemment démontré (Martin, 1991) ». Les remerciements seront omis dans la première soumission, et pourront être ajoutés dans la version définitive de l'article en cas d'acceptation.
** Comité d'organisation **
Co-présidente JEP : Sophie ROSSET, CNRS, LIMSI Co-président JEP : Nicolas AUDIBERT, Université Sorbonne Nouvelle - Paris 3, LPP Co-président TALN : Thierry HAMON, Université Paris 13, LIMSI Co-présidente TALN : Laurence DANLOS, Université Paris Diderot, ALPAGE Co-président RÉCITAL : Damien NOUVEL, INaLCO, ERTIM Co-présidente RÉCITAL : Ilaine WANG, Université Paris 10, MoDyCo
The third edition of TALAf will be held during the JEP-TALN-RECITAL conference, on July 4, 2016 at INALCO in Paris.
Natural language processing is booming in Africa. Indeed, in many countries, there is an ongoing official recognition of national languages, for instance:
In Niger, laws defining alphabets for Hausa, Kanuri, and Tamajaq Zarma were published in 1999. Since then, the National Assembly has set up simultaneous translation of the debates in three languages: French, Hausa and Zarma;
In Morocco, the Royal Institute of Amazigh Culture (IRCAM), which works for the promotion of Amazigh culture and development of the Berber language was founded by royal decree in 2001;
In Senegal, the recognition of national languages of the recognition was mentioned in the first article of the Constitution of 7 January 2001: 'The official language of the Republic of Senegal is French. The national languages are Diola, Malinke, Pular, Serer, Soninke, Wolof and other national language to be codified.' The Department of Technical Education, Vocational Training, Literacy and National Languages (METFPALN) is responsible for this. Since December 9, 2014, the Senegalese parliamentarians debates are translated simultaneously through an interpretation system in six national languages (Fulani, Serere, Wolof, Jola, Mandinka and Soninke) in addition to French, allowing the majority of members to speak in their mother tongue.
Moreover, a number of colleagues / African scholars trained in the North return to their country with the will to continue their work in local languages. There are also some Diasporas that have technological material allowing them to contribute directly online and on a voluntary basis.
Added to this, the development of bilingual education programs (official / national language) in primary schools in many countries is growing. The official language remaining mostly that of the former colonial country (French, English, Portuguese ...).
On the other hand, mobile phones are spreading fast: with 650 million units, Africa has surpassed the United States and Europe. In many areas, it is easier to install a mobile antenna than fixed lines. Therefore, the people who use a telephone for the first time do it with a mobile terminal. Applications are developed such as money transfer or dissemination of weather reports.
The funding of research projects on these languages can now be obtained from the 'Organisation Internationale de la Francophonie' with their calls for projects of the 'fonds francophone des inforoutes' (see eg DiLAF or flore projects) or the 'Agence Universitaire de la Francophonie'. France also supports projects on these languages through the National Agency for Research (see eg ALFFA project).
So the conditions are gathered for the development of natural language processing in Africa, both written and spoken.
In this context, the roles of TALAf workshop are:
bring together researchers in the field through meetings at the workshop but also with the talaf@imag.fr mailing list;
pooling knowledge using open source tools, standards (ISO, Unicode), and publishing the resources produced with an open license (Creative Commons) to avoid including the loss of information when a project stops and can not be resumed immediately for lack of resources;
develop a set of best practices based on the experience of researchers ; set up simple efficient methodologies based on free or very cheap software for the development of resources, exchange about techniques that can avoid the use of non-existent resources and finally avoid loss of time and energy.
TALAf workshops are supported by the non-profit organisation 'Lexicologie Terminologie Traduction': http://www.ltt.auf.org/index.php
We invite all researchers in natural language processing working on African languages, including Creole languages of Africa, whether written or oral, to submit a paper to this workshop.
TYPES OF COMMUNICATION
Publications should contain between 6 and 12 pages. Authors are invited to submit papers presenting original research particularly on the themes listed below.
French speaking authors are invited to write in French with a summary in the language of their choice. Non-French speaking writers can write in English with a summary in French and another in the language of their choice.
TOPICS
The workshop is open to research works on the following topics:
Resources:
? written corpora (monolingual, bilingual aligned or comparable)
? speech corpora (including transcription)
? lexicons, dictionaries and databases (monolingual, bilingual, multilingual)
? resources enrichment
? resources quality evaluation
Tools:
? morphological analyzers, spell-checkers
? syntactic analyzers, grammar checkers
? machine translation systems (empirical or rule-based)
? speech recognition
? text-to-speech synthesis
? transliteration
SELECTION CRITERIA
Submissions will be reviewed by at least two specialists of the domain.
The following points will be taken into account:
adequacy to the workshop topics
importance and originality of the contribution,
scientific and technical content precision,
organisation and clarity of the presentation.
SUBMISSIONS
The submission formats will be available for OpenOffice, Word and Latex and accessible from:
L?atelier TALPA s?inscrit dans le cadre de la conférence conjointe JEP-TALN-RECITAL qui aura lieu dans les nouveaux locaux de l?INALCO (Paris 13e). Il s?agit de la première édition de cet atelier. Il vise à favoriser les échanges autour des outils de traitement automatique appliqués à de la parole dite « atypique » ou « non-standard ». Les adjectifs « non-standard », « atypique » ou encore « non-prototypique » sont utilisés pour désigner les types de parole qui, d?une manière ou d?une autre, présentent des différences identifiables par rapport à un « standard », ou, autrement dit, par rapport à une forme canonique de parole. La recherche dans ce domaine tente de caractériser les variations de la parole qui peuvent être normales ou anormales selon les cas. En ce sens, nous pouvons citer, de manière non exhaustive, les cas d?étude suivants, qui répondraient pleinement au thème de cet atelier :
Parole d?apprenants d?une L2,
Parole de locuteurs ayant des troubles de la voix et de l?élocution,
Accents étrangers, régionaux et sociaux,
Parole d?enfants, de personnes âgées,
Parole stressée, fatiguée, avec de lourdes charges cognitives.
Toutes les applications qui y sont liées sont également concernées par cet appel : aide à l?apprentissage d?une langue, aide à la réhabilitation d?une pathologie de la voix et de la parole, par exemple.
Déroulement
Une session poster d?une heure et demie de présentation des travaux des participants
Une session pratique d?une durée de 45 minutes/1 heure visant à favoriser les échanges de manière informelle sous la forme d?une table ronde. Plus d?informations sur le site Web de l?atelier.
Types de communication
Les soumissions prendront la forme d?un résumé, rédigé en français ou en anglais pour les non-francophones, d?une taille maximale de 1000 mots, les références bibliographiques incluses, limitées à un nombre de 10 références au plus. Il n?est et ne sera pas demandé d?article complet, les actes de l?atelier seront une compilation des résumés acceptés qui sera mise en ligne.
Modalités de soumission
Il est demandé d?utiliser la feuille de style LaTeX, modèle Word ou modèle LibreOffice suivants (adaptés de ceux de la conférence JEP-TALN-RECITAL) :
Après réception des soumissions, les organisateurs enverront un mail aux candidats pour demander s?ils peuvent et souhaitent contribuer également à la session pratique. Ceci pourra prendre diverses formes : proposer des échantillons courts de parole atypique avec transcription orthographique, décrire un retour d?expérience sur l?utilisation d?un outil, faire la démonstration d?un outil, exposer les problèmes/ limites d?un outil automatique. Les organisateurs collecteront alors ces données/informations pour valider la possibilité de les intégrer à la partie pratique de l?atelier.
Les résumés sont à soumettre sous forme de PDF à l?adresse suivante :
The 2nd Workshop on Language Teaching, Learning and Technology is going to take place in San Francisco on September 6 and 7.
June 12, 2016: paper submission deadline
June 26, 2016: notification of paper acceptance
July 10, 2016: camera-ready paper submission deadline
September 6/7, 2016 workshop
The LTLT workshop intends to join researchers across countries on the topic of language teaching/learning. Papers submitted here do not have to employ any technology yet. We are looking for contributions from users that may not be aware of all the possibilities that the technologies have to offer to solve educational research problems. What these papers bring to the table are problem statements and data collections that the speech and text processing community may in turn not be aware of. Thus we are looking for symbioses between the two disciplines in research about learning/teaching language. It is important for both areas to get to know each other's research questions and potential application for technologies.
This goal will be achieved through collocation with workshops that are associated with Interspeech (focusing on technology for automatic processing and synthesis of speech and text) that allows you to meet people with similar interests, share your work and forge new interactions across disciplines. In doing so, we are looking for a broad range of contributions from didactics, psychology and pedagogy from researchers interested in bridging the current gap to automation. Demonstrations as well as samples of data collections and annotations are welcome.
This workshop is endorsed by ISCA and organized by the Special Interest Group for Children (SIG-CHILD) group that has regular WOCCI workshops.
Topics of Interest include but are not limited to:
Data collection, methods, annotation, recognition, analysis, diagnostic, progression of skills, for example in:
Handwriting
Spoken interaction
Story telling
Text production
Spelling errors
Evaluation of L1/L2 teaching methods
Teaching L2 Kids in an L1 class environment (many classes have a large number of multilingual children in L1 classrooms whose parents to not speak the L1 language)
Issues in majority language learning environments for L1 and L2 learners
Models of learning
Applications for teaching, self-learning, classroom learning
Giving Feedback
Technology in the classroom
Games for language learning
Other analyses and ideas that have to do with language teaching
The 2nd Workshop on Language Teaching, Learning and Technology is going to take place in San Francisco on September 6 and 7.
June 12, 2016: paper submission deadline
June 26, 2016: notification of paper acceptance
July 10, 2016: camera-ready paper submission deadline
September 6/7, 2015 workshop
The 5th Workshop on Child Computer Interaction (WOCCI 2016) will be held in San Francisco on 6-7th of September, 2016. The Workshop is a satellite event of the 17th Annual Conference of the International Speech Communication Association (INTERSPEECH 2016), which will take place in the same city September 8-12, 2016. WOCCI 2016 will be held at the offices of Educational Testing Services (ETS).
This workshop aims to join researchers and practitioners from universities and industry working in all aspects of child-machine interaction including computer, robotics and multi-modal interfaces. Children are special both at the acoustic/linguistic level as well as the interaction level. The Workshop provides a unique opportunity for bringing together different research communities from cognitive science, robotics, speech processing, linguistics as well as applied areas such as medical and educational technologies. Various state-of-the-art components can be presented here as key components for the next generation of child-centered computer interaction. Technological advances are increasingly necessary in a world where education and health pose growing challenges to the core wellbeing of our societies. Noticeable examples are remedial treatments for children with or without disabilities and capabilities for providing individualized attention. The Workshop will serve as a venue for presenting recent advancements in core technologies as well as experimental systems and prototypes.
Papers are solicited on any technical areas relevant to the workshop. The technical scope of the workshop includes, but it is not limited to:
Speech Interfaces: acoustic and linguistic analysis of children's speech, discourse analysis of spoken language in child machine interaction, age-dependent characteristics of spoken language, automatic speech recognition for children and spoken dialogue systems
Multi-modality and Robotics: multi-modal child machine interaction, multi-modal input and output interfaces, including robotic interfaces, intrusive, non-intrusive devices for environmental data processing, pen or gesture/visual interfaces
User Modelling: user modelling and adaptation, usability studies accounting for age preferences in child machine interaction
(2016-09-12) 19th International Conference on TEXT, SPEECH and DIALOGUE (TSD 2016), Brno, Czech Republic
TSD 2016 - FIRST CALL FOR PAPERS *****************************
Nineteenth International Conference on TEXT, SPEECH and DIALOGUE (TSD 2016) Brno, Czech Republic, 12-16 September 2016 http://www.tsdconference.org/
The conference is organized by the Faculty of Informatics, Masaryk University, Brno, and the Faculty of Applied Sciences, University of West Bohemia, Pilsen. The conference is supported by International Speech Communication Association.
Venue: Brno, Czech Republic
THE SUBMISSION DEADLINES:
March 15 2016 ............ Submission of abstracts March 22 2016 ............ Submission of full papers
Submission of abstract serves for better organization of the review process only - for the actual review a full paper submission is necessary.
TSD SERIES
TSD series evolved as a prime forum for interaction between researchers in both spoken and written language processing from all over the world. Proceedings of TSD form a book published by Springer-Verlag in their Lecture Notes in Artificial Intelligence (LNAI) series. TSD Proceedings are regularly indexed by Thomson Reuters Conference Proceedings Citation Index. Moreover, LNAI series are listed in all major citation databases such as DBLP, SCOPUS, EI, INSPEC or COMPENDEX.
The TSD 2016 conference will be accompanied by a one-day satellite workshop
Community-based Building of Language Resources, CBBLR
The main topic of the workshop is directed at building new language resources, especially for languages with no or too little existing language resources. The workshop is organized in cooperation with the HaBiT CZ-NO project Consortium, submissions from other resource development projects are more than welcomed. The workshop submissions will undergo two separate review processes - the best papers which will succeed in both review processes (by the TSD 2016 Conference PC and CBBLR Workshop 2016 PC) will be published in the TSD 2016 Springer Proceedings, all other accepted CBBLR workshop papers will be published in a separate proceedings with ISBN. The CBBLR workshop will take place on September 12 2016 in the conference venue.
The TSD 2016 conference will be directly followed by a meeting of the working groups and management committee of the
Topics of the conference will include (but are not limited to):
Corpora and Language Resources (monolingual, multilingual, text and spoken corpora, large web corpora, disambiguation, specialized lexicons, dictionaries)
Speech Recognition (multilingual, continuous, emotional speech, handicapped speaker, out-of-vocabulary words, alternative way of feature extraction, new models for acoustic and language modelling)
Tagging, Classification and Parsing of Text and Speech (morphological and syntactic analysis, synthesis and disambiguation, multilingual processing, sentiment analysis, credibility analysis, automatic text labeling, summarization, authorship attribution)
(2016-09-13) CfP Workshop on Machine Learning in Speech and Language Processing (MLSLP), San Francisco, CA, USA
*** Call for Papers/Abstracts:
*** Workshop on Machine Learning in Speech and Language Processing (MLSLP)
*** September 13, 2016
*** Google San Francisco, CA, USA
MLSLP is a workshop of SIGML, the ISCA SIG on machine learning in speech and language processing. Prior workshops were held in 2011 and 2012. While research in speech and language processing has always involved machine learning (ML), current research is benefiting from even closer interaction between these fields. Speech and language processing is continually mining new ideas from ML and ML, in turn, is devoting more interest to speech and language applications. This workshop aims to be a venue for identifying and incubating the next waves of research directions for interaction and collaboration. The workshop will not be yet another venue for applications of deep learning to speech and language processing, as this is already well covered by major conferences. It will, however, include new directions for deep learning in speech/language, as well as other emerging ideas. In general, the workshop will (1) discuss the emerging research ideas with potential for impact in speech/language and (2) bring together relevant researchers from ML and speech/language who may not regularly interact at conferences.
*** Paper Submission
Prospective authors are invited to submit 2-page abstracts or 4-6 page papers through the workshop web site. Each paper/abstract will be reviewed by at least two reviewers.
*** Important Dates
May 20: Submission deadline
June 17: Accept/reject decisions sent
June 30: Final papers/abstracts due
*** Invited Speakers
Confirmed speakers thus far include Ian Goodfellow, Fei Sha, and Kai Yu. Additional speakers TBA!
The 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2016) will be located in the University of Southern California Institute for Creative Technology, Los Angeles, CA, USA. SIGDIAL will be held September 13-15.
The SIGDIAL venue provides a regular forum for the presentation of cutting edge research in discourse and dialogue to both academic and industry researchers. Continuing with a series of sixteen successful previous meetings, this conference spans the research interest areas of discourse and dialogue. The conference is sponsored by the SIGdial organization, which serves as the Special Interest Group in discourse and dialogue for both ACL and ISCA.
TOPICS OF INTEREST
We welcome formal, corpus-based, system-building or analytical work on discourse and dialogue including but not restricted to the following themes and topics:
- Discourse Processing and Dialogue Systems - Corpora, Tools and Methodology - Pragmatic and/or Semantic Modeling - Computational Sociolinguistics - Collaborative Process Analysis - Dimensions of Interaction - Open Domain Dialogue - Style, Voice and Personality in Spoken Dialogue and Written Text - Applications of Dialogue and Discourse Processing Technology - Novel Methods for Generation Within Dialogue
Call for Special Session Proposals
The SIGDIAL organizers welcome the submission of special session proposals. A SIGDIAL special session has the length of a regular session at the conference and may be organized as a poster session, a poster session with panel discussion, or an oral presentation session. Note that Special Session papers can include papers that appear in the SIGDIAL proceedings and/or papers which do not appear in the proceedings. The only firm requirement is that papers which appear in the SIGDIAL proceedings must follow the same review process as normal SIGDIAL papers. Reviews for these papers are managed by the PC as usual. The special session organizers may suggest reviewers for the special session, but that is the extent of their involvement in reviewing special session papers which appear in the SIGDIAL proceedings. Special session organizers can decide how to handle SIGDIAL rejected papers--for example, they may invite papers which will not appear in the proceedings to still be presented. Special sessions may, at the discretion of the SIGDIAL organizers, be held as parallel sessions.
Those wishing to organize a special session should prepare a two-page proposal containing: (i) Summary of the topic of the special session; (ii) List of organizers and sponsors; (iii) List of people who may submit and participate; (iv) Requested format (poster/panel/oral session).
These proposals should be sent to conference[at]sigdial.org by the special session proposal deadline. Special session proposals will be reviewed jointly by the general and program co-chairs.
Special Session Proposal Deadline: Tuesday, 1 March 2016 (23:59, GMT-11) Special Session Notification: Sunday, 27 March 2016
* General SIGDIAL call for papers will be posted in Feb 2016.
SIGDIAL 2016 ORGANIZING COMMITTEE
General Chairs Raquel Fernandez, University of Amsterdam, Netherlands Wolfgang Minker, Ulm University, Germany
Program Chairs Giuseppe Carenini, The University of British Columbia, Canada Ryuichiro Higashinaka, Nippon Telegraph and Telephone Corporation, Japan
Local Chairs Ron Artstein, University of Southern California, USA Alesia Gainer, University of Southern California, USA
Mentoring Chair Pierre Lison, University of Oslo, Norway
Sponsorships Chair Ethan Selfridge, Interactions Corporation, USA
SIGdial President Amanda Stent, Yahoo! Labs, USA
SIGdial Vice President Jason Williams, Microsoft Research, USA
SIGdial Secretary/Treasurer Kristiina Jokinen, University of Helsinki, Finland _______________________________________________ SIGdial mailing list SIGdial@list.sigdial.org
(2016-10-17) The 10th International Symposium on Chinese Spoken Language Processing (ISCSLP), Tianjin, China
The 10th International Symposium on Chinese Spoken Language Processing
(ISCSLP 2016)
October 17 - 20, 2016
Tianjin, China
Call for Papers
The 10th International Symposium on Chinese Spoken Language Processing (ISCSLP2016) will be held on October 17-20, 2016 in Tianjin, China. ISCSLP is a biennial conference for scientists, researchers, and practitioners to report and discuss the latest progress in all theoretical and technological aspects of spoken language processing. While the Chinese language is emphasized, works on other languages that may be applied to Chinese speech and language are also encouraged.
Conference Website: http://www.iscslp2016.org
Topics of interest for submission include, but are not limited to the followings:
1. Speech Production and Perception
2. Speech Analysis
3. Speech Coding
4. Speech Enhancement
5. Hearing Aids and Cochlear Implant
6. Phonetics and Phonology
7. Corpus-based Linguistics
8. Speech and Language Disorders
9. Speech Recognition
10. Spoken Language Translation
11. Speaker, Language, and Emotion Recognition
12. Speech Synthesis
13. Language Modeling
14. Speech Prosody
15. Spoken Dialog Systems
16. Machine Learning Techniques in Speech and Language Processing
17. Voice Conversion
18. Indexing, Retrieval and Authoring of Speech Signals
19. Multi-Modal Interfaces
20. Speech and Language Processing in Education
21. Spoken Language Resources and Technology Evaluation
22. Applications of Spoken Language Processing Technology
23. Singing Voice Processing
24. Others
The working language of ISCSLP is English. Prospective authors are invited to submit full-length, five-page papers in any of the areas listed above. All papers will be handled and reviewed electronically and details can be found in the conference website http://www.iscslp2016.org. ISCSLP 2016 also invites proposals of special sessions and welcomes exhibitions of products and demos of research prototypes in the areas relevant to the conference. Please refer to the conference website for details of submission procedures.
Important Dates:
Regular and special session paper submission deadline: June 17, 2016
Notification of paper acceptance: August 05, 2016
Camera-ready paper upload deadline: August 19, 2016
Author’s registration deadline: September 02, 2016
ISCSLP 2016 will be hosted by Tianjin University, the first modern university in China and the pioneer of modern higher education in China. Tianjin was the ancient port city of Beijing, and now is the third largest city of China with a population of over 10 million people. It has a rich history and many examples of old British and Italian architecture. The famous Italian concession area has the largest cluster of old Italian architecture outside of Italy. Tianjin is near the coast and is located 85 miles east of Beijing, only 30 minutes by bullet train. Downtown 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 to attend the ISCSLP2016.
