![]() |
ISCApad #196 |
Sunday, October 12, 2014 by Chris Wellekens |
3-3-1 | (2014-10-14) 2nd INTERNATIONAL CONFERENCE ON STATISTICAL LANGUAGE AND SPEECH PROCESSING, Grenoble, France2nd INTERNATIONAL CONFERENCE ON STATISTICAL LANGUAGE AND SPEECH PROCESSING SLSP 2014 Grenoble, France October 14-16, 2014 Organised by: Équipe GETALP Laboratoire d’Informatique de Grenoble Research Group on Mathematical Linguistics (GRLMC) Rovira i Virgili University http://grammars.grlmc.com/slsp2014/ ********************************************************************************** PROGRAM Tuesday, October 14 9:00 - 10:00 Registration 10:00 - 10:15 Opening 10:15 - 11:05 Roger K. Moore: Spoken Language Processing: Time to Look Outside? - Invited Lecture 11:05 - 11:35 Coffee Break 11:35 - 12:50 Georgios Kontonatsios, Claudiu Mihaila, Ioannis Korkontzelos, Paul Thompson, and Sophia Ananiadou: A Hybrid Approach to Compiling Bilingual Dictionaries of Medical Terms from Parallel Corpora Wei Liu, Zhipeng Chang, and William J. Teahan: Experiments with a PPM Compression-based Method for English-Chinese Bilingual Sentence Alignment Chi-kiu Lo and Dekai Wu: BiMEANT: Integrating Cross-lingual and Monolingual Semantic Frame Similarities in the MEANT Semantic MT Evaluation Metric 12:50 - 14:20 Lunch 14:20 - 15:35 Mathias Verbeke, Vincent Van Asch, Walter Daelemans, and Luc De Raedt: Lazy and Eager Relational Learning using Graph-Kernels Mohamed Amine Boukhaled, and Jean-Gabriel Ganascia: Probabilistic Anomaly Detection Method for Authorship Verification Uli Fahrenberg, Fabrizio Biondi, Kevin Corre, Cyrille Jegourel, Simon Kongshj, and Axel Legay: Measuring Global Similarity between Texts 16:00 - 18:00 Touristic visit Wednesday, October 15 9:00 - 9:50 Claire Gardent: Syntax and Data-to-Text Generation - Invited Lecture 9:50 - 10:05 Break 10:05 - 11:20 Borbála Siklósi and Attila Novák: Identifying and Clustering Relevant Terms in Clinical Records Using Unsupervised Methods Amine Abdaoui, Jérôme Azé, Sandra Bringay, Natalia Grabar, and Pascal Poncelet: Predicting Medical Roles in Online Health Fora Ekaterina Pronoza, Elena Yagunova, and Svetlana Volskaya: Corpus-based Information Extraction and Opinion Mining for the Restaurant Recommendation System 11:20 - 11:50 Coffee Break and Group Photo 11:50 - 13:05 Raúl Ernesto Gutierrez de Piñerez Reyes and Juan Francisco Díaz-Frías: Informal Mathematical Discourse Parsing with Conditional Random Fields Waad Ben Kheder, Driss Matrouf, Pierre-Michel Bousquet, Jean-François Bonastre and Moez Ajili: Robust Speaker Recognition Using MAP Estimation of Additive Noise in i-vectors Space Arseniy Gorin and Denis Jouvet: Structured GMM Based on Unsupervised Clustering for Recognizing Adult and Child Speech 13:05 - 14:35 Lunch 14:35 - 16:35 Visit to the Domus apartment Thursday, October 16 9:00 - 9:50 Martti Vainio: Phonetics and Machine Learning: Hierarchical Modelling of Prosody in Statistical Speech Synthesis - Invited Lecture 9:50 - 10:05 Break 10:05 - 11:20 Gábor Kiss and Klára Vicsi: Physiological and Cognitive Status Monitoring on the Base of Acoustic-phonetic Speech Parameters Barbara Schuppler, Sebastian Grill, André Menrath, and Juan A. Morales-Cordovilla: Automatic Phonetic Transcription in Two Steps: Forced Alignment and Burst Detection Mian Du, Matthew Pierce, Lidia Pivovarova, and Roman Yangarber: Supervised Classification using Balanced Training 11:20 - 11:50 Coffee Break 11:50 - 13:05 Márius Šajgalík, Michal Barla, and Mária Bieliková: Exploring Multidimensional Continuous Feature Space to Extract Relevant Words Zhemin Zhu, Djoerd Hiemstra, and Peter Apers: Linear Co-occurrence Rate Networks (L-CRNs) for Sequence Labeling Théodore Bluche, Hermann Ney, and Christopher Kermorvant: Handwriting Recognition with Deep and Recurrent Neural Networks 13:05 - 13:15 Closing
| |||||||||||||||||||||||||
3-3-2 | (2014-10-15) Deuxième appel à inscription à l'Ecole d'Automne en Recherche d’Information Et Applications, Région Grenobloise, France
********************************************************************** Deuxième appel à inscription à l'Ecole d'Automne en Recherche d’Information Et Applications. 15-17 Octobre 2014 Domaine de Parménie – Région Grenobloise ********************************************************************** Nous avons le plaisir de vous annoncer la tenue de l'Ecole d'Automne en Recherche d’Information Et Applications, qui se tiendra à Izeaux, à 30 kilomètres au nord-est de Grenoble. EARIA (École d'Automne en Recherche d'Information et Application) a pour objectif principal la formation des doctorants dans le domaine de la Recherche d'Information (RI). Elle est organisée en 2014 par l'équipe Modélisation et Recherche d'Information Multimédia (MRIM) du Laboratoire d'Informatique de Grenoble (LIG) avec le support de l'Association Francophone de Recherche d'Information et Applications (ARIA http://www.asso-aria.org). L'ARIA est une société savante, association loi 1901, ayant pour but de promouvoir le savoir et les connaissances du domaine de la Recherche d'Information. Cette école permet d'échanger et de faire le point sur les dernières avancées scientifiques et technologies liées à l'indexation automatique et à la recherche des textes multilingues, des images, des vidéos, permettant de construire des Systèmes de Recherche d'Information Multimédia. Ces systèmes sont au cœur des futurs moteurs de recherche du WEB. Les cours sont organisés sur 4 demi-journées (du mercredi 15 octobre 2014 midi au vendredi 17 octobre midi) et offrent un cadre d'échange convivial tant autour des fondements que des thèmes novateurs dans le domaine de la RI, abordés par des chercheurs français et européens faisant autorité dans le domaine. EARIA a vocation à se tenir tous les deux ans et offre une occasion privilégiée de rencontres et de discussions entre séniors du domaine et jeunes chercheurs, permettant ainsi à ces derniers de mieux situer leur projet de recherche. Les domaines couverts par les cours de cette école d'automne sont présentés en 8 sessions, et couvrent aussi bien des éléments généraux du domaine (comme une introduction, des éléments de modélisation théoriques, des aspects logiciels, des éléments expérimentaux), et des aspects plus spécialisés. Parmi les thèmes traités par cette école nous avons : • L'introduction à la Recherche d'Information – les bases communes (M. Boughanem, E. Gaussier) • Le Traitement Automatique des Langues Naturelles et l'Extraction d'Information pour la Recherche d'Information (I. Tellier); • La Recherche d'Information multimédia (G. Quénot, G. Linares); • La Recherche d'Information sociale (J. Kamps); • La Recherche d'Informations sémantique (J.-P. Chevallet);
| |||||||||||||||||||||||||
3-3-3 | (2014-10-16) CfP MediaEval 2014 Multimedia Benchmark Evaluation, Barcelona (SP) --------------------------------------------------
| |||||||||||||||||||||||||
3-3-4 | (2014-10-16) Journées de pausologie à Montpellier France Deadline extension
Journées de pausologie http://itic.univ-montp3.fr/pausologie/
D’un point de vue purement formel, une séquence de parole peut être décrite comme une succession de sons entrecoupée par des phases silencieuses. Si la phonétique s’est largement appliquée à décrire ces séquences sonores du point de vue de leurs caractéristiques articulatoires, de leur dimension acoustique et de leurs conséquences au niveau perceptif, les pauses ont fait l’objet d’un nombre d’études moins conséquent, alors même qu’un certain nombre de recherches (Goldman-Eisler, 1968 par ex.) ont révélé la nécessité de marquer de brèves interruptions lors de la production de la parole.
Ce caractère essentiel de la pause s’explique notamment par le fait qu’elle est le reflet à la fois du mouvement respiratoire mais aussi d’une activité cognitive importante. En effet, la pause permet au locuteur de reprendre son souffle mais aussi de planifier le contenu de son message pour structurer son énoncé et le mettre en scène, comme dans le cas des discours politiques par exemple (Duez, 1999 par ex.). En outre, la pause est également l’un des éléments révélant la fin d’un tour du parole et le signal du début de la prise de parole pour l’interlocuteur (Sacks et al., 1974). A l’écrit, les fonctions prosodiques, mais aussi syntaxiques et sémantiques, de la pause sont traditionnellement marquées par des signes de ponctuation dont l’interprétation a varié au cours de l’histoire (Catach, 1994 ; 2001).
La dimension cognitive de la pause qui a été évoquée plus haut permet également d’exploiter ce paramètre rythmique en linguistique clinique dans la mesure où la pause, prise en tant que disfluence, est révélatrice des capacités langagières de l’individu : la localisation et la durée des pauses peuvent en effet servir d’indices pour respectivement identifier des difficultés pathologiques d’accès au lexique (Gayraud et al., 2011) ou pour différencier une disfluence classique et un bégayage (Starkweather, 1987 ; Hirsch et al., 2012).
Les propositions de communication devront répondre à une des thématiques suivantes :
Le lien avec le sujet du colloque devra être explicité dans le résumé. Par ailleurs, des propositions n’entrant pas directement dans l’une des thématiques proposées ci-dessus peuvent également être acceptées à la condition que soit manifesté le lien avec le thème des Journées.
Bibliographie :
Catach N., (1994) La ponctuation : histoire et système, collection Que sais-je ?, n° 2818, Paris, PUF. Catach N. (2001) Histoire de l'orthographe française, éd. posthume réalisée par Renée Honvault, avec la collab. de Irène Rosier-Catach, collection Lexica, n° 9, Paris, Champion. Duez D. (1999), La fonction symbolique des pauses dans la parole de l'homme politique, Faits de langues, vol. 13, p. 91-97. Gayraud, F., Lee H.R., Barkat-Defradas, M. (2010), Syntactic and lexical context of pauses and hesitations in the discourse of Alzheimer patients and healthy elderly subjects, Clinical Linguistics & Phonetics, vol. 25(3):198-209 (DOI : 10.3109/02699206.2010.521612). Goldman-Eisler F. (1968) Psycholinguistics. Experiments in spontaneous speech, New York, Academic Press. Hirsch F., Monfrais-Pfauwadel M.C., Crevier-Buchman L., Sock R., Fauth C., Pialot H. (2012) Using nasovideofibroscopic data to observe abnormal laryngeal behavior in stutterers, Proceedings of the 7th World Congress on Fluency Disorders, 2-5 juillet, Tours. Sacks H., Schegloff E A., Jefferson G. (1974), A Simplest Systematics for the Organization of Turn-Taking for Conversation, Language, n° 50, 4, p. 696-735. Starkweather C. (1987), Fluency and Stuttering. Englewood Cliffs: Prentice Hall.
Comité Scientifique :
Barkat-Defradas Mélissa, Praxiling CNRS UMR5267-Université de Montpellier Bres Jacques, Praxiling CNRS-Université de Montpellier Delais-Roussare Elisabeth, CNRS-Université Paris 7 Paris Diderot, Dodane Christelle, CNRS-Université de Montpellier Ferré Gaëlle, Laboratoire de Linguistique de Nantes Gayraud Frédérique, Université Lyon 2 & CNRS (Dynamique du Langage UMR5596) Ghio Alain, Laboratoire Parole et Langage UMR 7309 CNRS - Université Aix-Marseille Goldman Jean-Phillipe, Université de Genève Hirsch Fabrice, Praxiling CNRS UMR5267-Université de Montpellier Kleiber Georges, Université de Strasbourg, EA 1339 Lilpa Rochet-Capellan Amélie, GIPSA Lab CNRS UMR 5216, Grenoble Simon Anne-Catherine, Université Catholique de Louvain Sock Rudolph, Université de Strasbourg, EA 1339 Lilpa Steuckardt Agnès, Praxiling CNRS UMR5267-Université de Montpellier Vaxelaire Béatrice, Université de Strasbourg, EA 1339 Lilpa
Comité d’Organisation :
Barkat-Defradas Mélissa, Université Paul Valéry, UMR5267 Praxiling Bellemouche Hacène, Université Paul Valéry, UMR5267 Praxiling Didirkova Ivana, Université Paul Valéry, UMR5267 Praxiling Dodane Christelle, Université Paul Valéry, UMR5267 Praxiling Hirsch Fabrice, Université Paul Valéry, UMR5267 Praxiling Maturafi Lavie, Université Paul Valéry, UMR5267 Praxiling Sauvage Jérémi, Université Paul Valéry, UMR5267 Praxiling
Calendrier : La date limite de soumission des propositions de communications (résumé de 500 mots hors bibliographie) a été repoussée au 30 Juin 2014 Les résumés sont à adresser à fabrice.hirsch@univ-montp3.fr ET melissa.barkat@univ-montp3.fr pour cette date. Date de notification aux auteurs : 15 juillet 2014 Journées d’Etudes de Pausologie : 16-17 octobre 2014
Soumission :
Les soumissions aux Journées de Pausologie se présentent sous la forme de résumés rédigés en français, d'une longueur maximale de 500 mots (hors bibliographie), police Times New Roman, 12pt, interligne simple. Les résumés devront être soumis au format PDF aux adresses suivantes : fabrice.hirsch@univ-montp3.fr ET melissa.barkat@univ-montp3.fr. Dans un souci d’anonymisation, ne figureront dans le fichier PDF que le titre de la proposition, le résumé et la bibliographie. Le nom des auteurs et leur affiliation devront être présents dans le courriel mais pas dans le fichier PDF.
Un article sera demandé à l’issue des Journées en vue d’une publication.
Pour toute question, écrire à : fabrice.hirsch@univ-montp3.fr
| |||||||||||||||||||||||||
3-3-5 | (2014-10-29) 14e Colloque International des Etudes créoles 14e Colloque International des Etudes créoles « Etudes créoles : bilan, enjeux et perspectives »
29 - 31 octobre 2014 ESPE, Aix-Marseille Université Aix-en-Provence
Organisé par le Comité International des Etudes créoles (CIEC), Avec le soutien du Laboratoire Parole et Langage (LPL UMR7309 CNRS AMU)
Présentation Le quatorzième colloque international des études créoles organisé par le Comité International des Etudes créoles (CIEC), avec le soutien de l’UMR 7309 (Laboratoire Parole et Langage), se tiendra à l'ESPE (AMU), à Aix-en-Provence. Il se propose de dresser un bilan des quarante dernières années de travaux dans le domaine – le premier colloque du CIEC a eu lieu en 1976, à Nice – et de réfléchir aux enjeux et perspectives des études créoles, dans leurs dimensions anthropologiques, littéraires et linguistiques. Suivant la tradition inaugurée à Nice, les colloques du CIEC s’intéressent d’abord aux langues créoles françaises dans leurs environnements multilingues et à la culture des formations sociales où ces langues sont en usage. Cependant, des contributions portant sur d’autres langues créoles et d’autres aires créolophones sont également encouragées.
Trois thèmes, abordés par des conférences plénières et par d’éventuels ateliers, seront traités : A. La description des langues créoles dans leurs environnements multilingues B. Les langues créoles et l’éducation C. Les littératures et l’anthropologie des pays de langue créole
Les thèmes du Colloque A. La description des langues créoles dans leurs environnements multilingues On se propose de dresser un bilan des recherches sur les langues créoles dans leurs environnements multilingues et de tracer quelques pistes pour l’avenir de ces travaux. Les communications présentées pourront porter sur des questions d'ordre théorique abordées en synchronie, tout autant que sur l’émergence et la formation des langues créoles. Elles pourront aborder les diverses dimensions des systèmes linguistiques et des pratiques langagières créoles en contexte multilingue
B. Langues créoles et éducation Le thème de l’aménagement des langues créoles (dictionnaires, grammaires, curriculums) et de l’éducation restent d’actualité bien que déjà abordés lors des conférences du Cap Vert (2005), d’Haïti (2008) et de Maurice (2012). Les pays souverains qui usent d’une langue créole française sont confrontés aux enjeux de l’éducation pour tous à l’école de base et à l’école moyenne. Dans ce contexte, le recours à la scolarisation en langue créole dans des systèmes plurilingues se pose avec une certaine acuité. Certains états tels les Seychelles, Haïti, dorénavant Maurice, ont un acquis dans le domaine scolaire qu’il convient d’interroger. Les Départements d’Outremer créolophones forts du statut de langue de France reconnu aux langues créoles, et des propositions des Etats Généraux du Multilinguisme dans les Outre-Mer (EGM-OM) et de la déclaration de Cayenne 2011, ont également des pratiques de scolarisation. Il convient de penser enfin, aux diasporas créoles à travers le monde, à commencer par la France hexagonale.
C. Littératures et anthropologie des pays de langue créole L’anthropologie des pays de langue créole a accompli durant ces dernières décennies de remarquables progrès. Elle semble aujourd’hui marquer le pas. Le 14ème Colloque des études créoles sera l’occasion d’en dresser le bilan et de réfléchir à de nouvelles perspectives. La production littéraire des îles créolophones de la Caraïbe et de l’Océan Indien s’est grandement développée durant ces dernières années en langue française et anglaise tout autant que dans les langues créoles. L’étude du renouveau des littératures et pratiques culturelles des pays de langue créole sera au coeur de ce thème.
Lieu ESPE, Aix-Marseille Université, 2 av. Jules Isaac, 13626 Aix-en-Provence
Comité scientifique Marlyse BAPTISTA (Université de Michigan, Ann Arbor) Michel DEGRAFF (Massachussetts Institute of Technology) Dominique FATTIER (Université de Cergy-Pontoise) Guillaume FON SING (LLF - Université Paris 7) Thomas KLINGLER (Université de Tulane, Nouvelle-Orléans) Sibylle KRIEGEL (LPL - Université d'Aix-Marseille) Jean Claude Carpanin MARIMOUTOU (Université de la Réunion) Salikoko MUFWENE (Université de Chicago) Ingrid NEUMANN-HOLZSCHUH (Université de Regensburg) Lambert Félix PRUDENT (Université des Antilles et de la Guyanne) Albert VALDMAN (Indiana University, Bloomington) Georges Daniel VERONIQUE (LPL - Université d'Aix-Marseille)
Comité d’organisation Carine ANDRE (LPL, CNRS, Université d'Aix-Marseille) Stéphanie DESOUS (LPL, CNRS, Université d'Aix-Marseille) Guillaume FON SING (LLF, Université Paris 7) Sibylle KRIEGEL (LPL, Université d'Aix-Marseille) Joëlle LAVAUD (LPL, CNRS, Université d'Aix-Marseille) Nadia MONSEGU (LPL, CNRS, Université d'Aix-Marseille) Claudia PICHON-STARKE (LPL, CNRS, Université d'Aix-Marseille) Georges Daniel VERONIQUE (LPL, Université d'Aix-Marseille)
Contact : colloqueciec.2014@gmail.com Site Web : http://lpl-aix.fr/~ciec2014/ Affiche : http://www.lpl-aix.fr/~fulltext/actualites/affiche_creoles_fini.pdf
| |||||||||||||||||||||||||
3-3-6 | (2014-10-30) French Prosody in Contact, Louvain la Neuve, Belgium
Chers collègues, Descriptif thématique de la journée (en anglais) : French Prosody in Contact The aim of this workshop is to bring together researchers working on the prosody of French in contact with other languages, and the prosody of other languages in contact with French. The notion of two languages being in contact is deliberately understood in its broadest sense, including the phenomena observed in areas where French is spoken concurrently with other languages and the interaction between an individual speaker’s L1 and L2 during language learning. The French prosodic system is typologically idiosyncratic because primary stress is not a lexically distinctive property, but is supra-lexically constrained. Distinguishing between stress, accentuation, phrasing and intonation is thus more difficult in French than in several other Indo-European and African languages. Previous studies have shown that the specificities of the French prosodic system are difficult to acquire for learners of French, and, conversely, have an impact on the second language learning performance of French native speakers. Furthermore, they are a source of regional variation in areas where French and other languages co-exist. During the workshop, specialists and young researchers will come together to present the results of studies on prosody when French is found in contact with: - African languages (Swahili, Lingala, Kirundi); - Germanic languages (Norwegian, German, Dutch, English); - Romance languages (Italian, Spanish). The workshop highlights corpus-based approaches, with authentic speaker productions from L1 and L2/learner corpora, while many of the presentations focus on perceptual experiments to assess issues such as the perception of regional accent, stress deafness and fluency. We hope that the workshop will foster a fruitful debate on aspects of the French prosodic system (such as initial stress, prosodic contours, rhythm etc.) and will highlight the theoretical and methodological issues inherent in the study of prosody in contact (e.g. the effects of the typological distance between source and target language, difficulties in assessing the existence of prosodic transfer etc.).
Bien cordialement,
| |||||||||||||||||||||||||
3-3-7 | (2014-11-03) CfP ACM Multimedia 2014 - Area on Music, Speech, and Audio Processing in Multimedia, Orlando, Florida, USACall for short and long paper contributions for ACM Multimedia 2014 -
Area on Music, Speech, and Audio Processing in Multimedia
November 3-7, 2014 Orlando, Florida, USA
(For general information and information on other areas check http://www.acmmm.org/2014/)
As a core part of multimedia data, the acoustic modality is of great importance as a source of
information that is orthogonal to other modalities like video or text. This allows for richer
information to be extracted when performing content analysis, as well as a rich mean of
communication of information. We are seeking strong technical submissions revolving around
music, speech and audio processing in multimedia. One topic of interest is submissions
performing an analysis of the acoustic signals in order to extract information from multimedia
content (e.g. what notes are being played, what is being said, or what sounds appear), or the
context (e.g. language spoken, age and gender of the speaker, localization using sound).
Another topic of interest is submissions performing synthesis of acoustic content for multimedia
purposes (e.g. speech synthesis, singing voices, acoustic scene synthesis). Furthermore, we are
also interested in ways to represent acoustic data as multimedia; for example, in symbolic form
(e.g. closed captioning of speech), in the form of sensor input and visual images (e.g. recordings
of gestures in musical performances). or others. Another topic of interest is applications that
involve the acoustic modality. The inclusion of acoustics opens up interesting possibilities for
novel multimedia interfaces and user interactions. In addition, contextual, social and affective
aspects play an important role when using acoustics, which can be seen, for example, in the
consumption and enjoyment of music, and the sound design of cinematic productions.
All submissions should maintain a clear relation to multimedia: there either should be an
explicit relation to multimedia items, applications or systems, or an application of a multimedia
perspective, in which information sources from different modalities are considered.
Topics of interest include, but are not limited to:
· Multimedia audio analysis and synthesis · Multimedia audio indexing, search, and retrieval
· Music, speech, and audio annotation, similarity measures, and evaluation
· Multimodal and multimedia approaches to music, speech, and audio
· Multimodal and multimedia context models for music, speech, and audio
· Computational approaches to music, speech, and audio inspired by other domains (e.g.
computer vision, information retrieval, musicology, psychology)
· Multimedia localization using acoustic information
· Social data, user models and personalization in music, speech, and audio
· Music, audio, and aural aspects in multimedia user interfaces
· Algorithms and applications of music, speech, and audio
· New and interactive musical instruments, systems and other music, speech, and audio
applications · Novel interaction interfaces using/with music, speech, and audio
· Music, speech, and audio coding, transmission, and storage for multimedia applications
Deadlines for long papers is March 31st, 2014 and for short papers is April 14th, 2014
For other deadlines please check http://www.acmmm.org/2014/important_dates.html
| |||||||||||||||||||||||||
3-3-8 | (2014-11-19) ALBAYZIN 2014 SEARCH ON SPEECH EVALUATION, Gran Canaria, SpainALBAYZIN 2014 SEARCH ON SPEECH EVALUATION The Spanish Thematic Network on Speech Technology (RTTH) and the ISCA Special Interest Group on Iberian Languages (SIG-IL) are pleased to announce the ALBAYZIN 2014 Search on Speech Evaluation, which will be carried out as part of Iberspeech 2014, a biennial event gathering the Spanish researchers on speech Technology. This year’s event will take place in Las Palmas de Gran Canaria (Spain), on November 19-21, 2014 (see http://iberspeech2014.ulpgc.es for details). Research groups worldwide are invited to participate in this evaluation. Here we just provide the key points. The full evaluation plan can be found in: http://iberspeech2014.ulpgc.es/index.php/albayzin/search-on-speech-evaluation **TASKS** The ALBAYZIN 2014 Search on Speech evaluation involves searching in audio content a list of terms/queries. This evaluation focuses on retrieving the appropriate audio files that contain any of those terms/queries. Four different tasks are defined: 1) KEYWORD SPOTTING (KWS), where the input to the system is a list of terms, which is known when processing the audio and hence word-based recognizers can be effectively used to hypothesize detections. 2) SPOKEN TERM DETECTION (STD), where the input to the system is a list of terms (as in the KWS task), but terms/queries are unknown when processing the audio. This is the same task as in NIST STD 2006 evaluation [1] and Open Keyword Search 2013 [2]. 3) QUERY-BY-EXAMPLE SPOKEN TERM DETECTION (QbE STD), where the input to the system is an acoustic example per query and hence a prior knowledge of the correct word/phone transcription corresponding to each query cannot be made. This task must generate a set of occurrences for each query detected in the audio files, along with their timestamps as output, as in the STD task. QbE STD is the same task as those proposed in MediaEval 2011, 2012 and 2013 [3]. 4) QUERY-BY-EXAMPLE SPOKEN DOCUMENT RETRIEVAL (QbE SDR), where the input to the system is composed of several acoustic examples per query and hence a prior knowledge of the correct word/phone transcription corresponding to each query cannot be made. This task must generate an output score for each of the provided queries, which reflects the probability that each of the queries appears in each audio file, and no information about the timestamp is required. Formally, given a spoken example of a given query q and a spoken document x (whose transcriptions are unknown), a QbE SDR system must carry out some kind of detection procedure and output a score s ∈ R, the higher (the more positive) the score the higher the likelihood that q appears in x. Note that systems are neither required to make a strong decision about whether or not q appears in x, nor to provide the time marks of the place (or places) where q appears. Systems are just required to produce a score, which must be computed by automatic means, with no human supervision. This is the same task as that proposed in MediaEval 2014 Query-by-Example Search on Speech (QUESST) [4]. **REGISTRATION** Interested groups must register for the evaluation before July 15th 2014, by contacting the organizing team at: javiertejedornoguerales@gmail.com luisjavier.rodriguez@ehu.es with CC to the Chairs of Iberspeech 2014(iberspeech2014@ulpgc.es), and providing the following information: Research group (name and acronym) Institution (university, research center, etc.) Contact person (name) Email **SCHEDULE** • June 30, 2014: Release of training and development data • July 15, 2014: Registration deadline • September 3, 2014: Release of evaluation data • September 30, 2014: Deadline for the submission of system outputs and description papers • October 15, 2014: Results distributed to participants • November 19-21, 2014: Evaluation Workshop at Iberspeech 2014 For more information, please follow the link to the Albayzin 2014 Search on Speech Evaluation: http://iberspeech2014.ulpgc.es/index.php/albayzin/search-on-speech-evaluation **REFERENCES** [1] http://www.itl.nist.gov/iad/mig/tests/std/2006/index.html [2] http://www.nist.gov/itl/iad/mig/openkws13.cfm [3] Florian Metze, Xavier Anguera, Etienne Barnard, Marelie Davel and Guillaume Gravier. 'Language Independent Search in Mediaeval's Spoken Web Search Task'. Computer Speech and Language, Special Issue on Information Extraction & Retrieval, 2014. [4] http://multimediaeval.pbworks.com/w/page/79432139/QUESST2014
| |||||||||||||||||||||||||
3-3-9 | (2014-12-01) CfP IEEE Global Conference on Signal and Information Processing - Atlanta Georgia 2014 Technical Program Chairs: Douglas Williams, Timothy Davidson, and Ghassan AlRegib The IEEE Global Conference on Signal and Information Processing (GlobalSIP) is a recently launched flagship conference of the IEEE Signal Processing Society. GlobalSIP’14 will be held in Atlanta, Georgia, USA, during the week of December 1, 2014. The conference will focus broadly on signal and information processing with an emphasis on up-and-coming signal processing themes. The conference will feature world-class speakers, tutorials, exhibits, and technical sessions consisting of poster or oral presentations. GlobalSIP’14 will be comprised of colocated symposia selected competitively based on responses to this call-for-symposium proposals. Symposium topics may include, but are not limited to:
Symposium proposals should include the title of the symposium; length of the symposium (one day or two days); projected selectivity of the symposium; paper length requirements (submission: from 2 to 6 pages, final: 4-6 pages, invited papers may be longer); names, addresses, and short CVs (up to 250 words) of the organizers, including the general organizers and the technical chairs; an up-to two page description of the technical issues that the symposium will address (including timeliness and relevance to the signal processing community; names of (potential) technical program committee members; name of (potential) invited speakers (up to 2 for one-day symposia and 4 for two-day ones)); and a draft call-for-papers. Please package everything in a single pdf file. More detailed information can be found at http://renyi.ece.iastate.edu/globalsip2014/cfs.html Symposium proposals should be emailed to Doug Williams (doug.williams@ece.gatech.edu) and Geoffrey Li (liye@ece.gatech.edu) according the following timeline: November 8, 2013: Symposium proposals due Tentative timeline for paper submission:
| |||||||||||||||||||||||||
3-3-10 | (2014-12-03) GlobalSIP Symposium: Machine Learning Applications in Speech Processing GlobalSIP Symposium: Machine Learning Applications in Speech Processing: Submission deadline June 16 This is a reminder of the upcoming submission deadline of June 16, for the Machine Learning Applications in Speech Processing symposium of the IEEE SPS GlobalSIP conference (Atlanta Georgia, December 3-5, 2014). The symposium is accepting papers, as the title suggests, that apply machine learning methods in interesting ways to speech processing tasks. For more information, please see http://www.ieeeglobalsip.org/symposium/mlasp.html
| |||||||||||||||||||||||||
3-3-11 | (2014-12-07) 3rd Dialog State Tracking Challenge (DSTC3). We are pleased to announce the opening of the third Dialog State Tracking Challenge (DSTC3). Complete information, including the challenge handbook, training data, evaluation scripts, and baseline trackers are available on the DSTC3 website: http://camdial.org/~mh521/dstc/ The Dialog State Tracking Challenge (DSTC) is a research challenge focused on improving the state of the art in tracking the state of spoken dialog systems. State tracking refers to accurately estimating the user's goal as a dialog progresses. Accurate state tracking is desirable because it provides robustness to errors in speech recognition, and helps reduce ambiguity inherent in language within a temporal process like dialog. In this challenge, participants are given labelled corpora of dialogs to develop state tracking algorithms. The trackers will then be evaluated on a common set of held-out dialogs which are released, un-labelled, during a one week period. This is a corpus-based challenge: participants do not need to implement a speech recognizer, a semantic parser, or an end-to-end dialog system. The first DSTC completed in 2013, with 9 teams participating and a total of 27 entries, with 9 papers presented at SIGDIAL 2013, advancing the state-of-the-art in several dimensions. DSTC2 introduced a completely new dataset, in a new domain (restaurant information), with more complicated and dynamic dialog states that may change throughout the dialog. DSTC2 concluded a few months ago, again with 9 participating teams (about half new) -- results have been submitted to and will be presented at a special session at SIGDIAL 2014. DSTC3 will focus on the task of adapting and expanding to a new domain, when there is a lot of labelled data in a smaller domain. The 'smaller domain' is the restaurants domain from DSTC2; the 'new extended domain' is a larger tourist information domain: DSTC3 includes restaurants and adds pubs and coffee shops, and more detail (slots) for restaurants relative to the DSTC2 data. Participants are encouraged to submit papers describing their work to SLT 2014, whose deadline will be approx. 20 July. The organisers are awaiting confirmation of a proposed special session at the conference. DSTC3 schedule: - 4 April 2014 : Labelled tourist information seed set released - 9 June 2014 : Unlabelled tourist information test set released - 16 June 2014 : Tracker output on tourist information test set due - 23 June 2014 : Results on tourist information test set given to participants - 20 July 2014 : SLT paper deadline (approximate) - 7-10 Dec 2014 : SLT workshop (Lake Tahoe, Nevada, USA) The training data, scoring scripts, baselines, domain ontology and database are all available for public download. Prospective participants are strongly encouraged to join the mailing list, to ensure you receive notifications of updates to data or scripts, and are included in discussions about the challenge. To join, email listserv@lists.research.microsoft.com with 'subscribe DSTC' in the body of the message (without quotes). Feel free to direct questions to the organizers. We hope you will consider participating! DSTC3 organizers Matt Henderson (lead) - Cambridge University [matthen@gmail.com] Blaise Thomson - Cambridge University [brmt2@cam.ac.uk] Jason D. Williams - Microsoft Research [jason.williams@microsoft.com] DSTC3 advisory board Bill Byrne - University of Cambridge Paul Crook - Microsoft Research Maxine Eskenazi - Carnegie Mellon University Milica Gasic - University of Cambridge Helen Hastie - Herriot Watt Kee-Eung Kim - KAIST Sungjin Lee - Carnegie Mellon University Oliver Lemon - Herriot Watt Olivier Pietquin - SUPELEC Joelle Pineau - McGill University Deepak Ramachandran - Nuance Communications Brian Strope - Google Steve Young - University of Cambridge
| |||||||||||||||||||||||||
3-3-12 | (2014-12-07)The 2014 IEEE Spoken Language Technology Workshop (SLT 2014) , South Lake Tahoe, California/Nevada, USA The 2014 IEEE Spoken Language Technology Workshop (SLT 2014) will be held in South Lake Tahoe, California and Nevada, on Dec 7-10, 2014. The main theme of the workshop will be 'machine learning in spoken language technologies'. One of our goals is to increase both intra and inter community interaction, by means of (inter alia)
Following tradition from the last two SLT workshops in 2010 (Berkeley, CA) and 2012 (Miami, FL), we are looking forward to hosting challenges and special or themed sessions. Submission of papers in all areas of spoken language technology is encouraged, with emphasis on the following topics: · Speech recognition and synthesis · Spoken language understanding · Spoken dialog systems · Spoken document summarization · Machine translation for speech · Question answering from speech · Speech data mining · Spoken document retrieval · Spoken language databases · Multimodal processing · Human/computer interaction · Educational and healthcare applications · Assistive technologies · Natural Language Processing Important Deadlines Paper Submission Monday, July 21, 2014 Notification of Acceptance Friday, September 5, 2014 Demo Submission September 2014 Demo Acceptance October 2014 Early registration deadline October 17, 2014 Workshop December 7-10, 2014 Submission Procedure
Prospective authors are invited to submit full-length, 4-6 page papers, including figures and references, to the SLT 2014 website. All papers will be handled and reviewed electronically. Please note that the submission dates for papers are strict deadlines.
| |||||||||||||||||||||||||
3-3-13 | (2014-12-10) 4th International Conference on Acoustics and Vibration (ISAV2014), Tehran, Iran
The Iranian Society of Acoustics and Vibration (ISAV) has the great pleasure of inviting you to the 4th International Conference on Acoustics and Vibration (ISAV2014). ISAV2014 is jointly organized by ISAV and Iran University of Science and Technology and will be held in Tehran, Iran from 10-11 December, 2014. Following three successful conferences in three last years (ISAV2011, ISAV2012 and ISAV2013), we look forward to welcoming you to another memorable and exciting ISAV conference in 2014. Through keynote lectures and oral and poster presentations, the conference will present an overview of the latest developments in theoretical and applied acoustics and vibration. We cordially invite you to submit your papers for oral and poster sessions through the conference website www.isav.ir/2014. We also invite sponsors and exhibitors to participate in the conference exhibition where they can present their latest scientific and industrial achievements, advertise their new products and services, and learn about the latest developments in acoustics and vibration. Please use the link here to go to the conference website. The deadline for paper submission is 22th June 2014. We look forward to seeing you at ISAV2014 in December 2014 in Tehran. Sincerely, ISAV2014 Secretariat
| |||||||||||||||||||||||||
3-3-14 | (2014-12-23) CfP International Conference on Human Machine Interaction, New Delhi IndiaCall for papersInternational Conference on Human Machine Interaction 2014 23 – 25, December 2014 http://intconfhmi.com In association with SETIT, Sfax University, Tunisia. and ASDF (Association of Scientists, Developers and Faculties) Chennai Chapter, we will organize the International Conference HMI 2014 which will be held in New delhi -INDIA. Human Machine Interaction (HMI), is a main annual research conference aimed at presenting current research being carried out. The idea of the conference is for the scientists, scholars, engineers and students from the Universities all around the world and the industry to present ongoing research activities, and hence to foster research relations between the Universities and the industry. HMI 2014 is co-sponsored by Association of Scientists, Developers and Faculties and SETIT, Sfax University, Tunisia and technical co-sponsored by many other universities and institutes. Area of Submission
Topics of interest for HMI is widely declared for the above, but not limited to. Conference Registration Fees Rebate (Discount)We are pleased to inform you that the organizing committee of the HMI2014 allocates a financial support for all participants from developing or emerging countries. This Financial support of among of 150 Dollars is available to help participants to attend HMI2014 You can find more details in: http://intconfhmi.com/register.html
We are waiting for seeing you in India. NB : A select number of Post Conference Excursions will take place during 5 days. As examples : 1 Day Tour to Taj Mahal, Agra Fort, Mathura in AC Bus : 25 $ per person 1 Day Tour to Qutub Minar, Parliament, Lotus Temple, India Gate, Gandhi Smiriti, Red Fort, Humayun's Tomb, Rajghat: 25 $ per person
Best Regards Mohamed Salim BOUHLEL General Co-Chair, HMI2014 Head of Research Unit: Sciences & Technologies of Image and Telecommunications ( Sfax University ) GSM +216 20 200005
| |||||||||||||||||||||||||
3-3-15 | (2015-01-12) International Conference on Bio-inspired Systems and Signal Processing, Lisbon, PortugalInternational Conference on Bio-inspired Systems and Signal Processing BIOSIGNALS website: http://www.biosignals.biostec.org/ January 12 - 15, 2015 Lisbon, Portugal Technical Co-sponsorship by: BMES, ESEM and IEEE EMBS In Cooperation with: EUROMICRO, ISfTeH, AAAI and EURASIP Sponsored by: INSTICC INSTICC is Member of: WfMC, OMG and FIPA Media Partner: BMC Medical Informatics and Decision Making Logistics Partner: SCITEVENTS IMPORTANT DATES: Position Paper Submission: October 9, 2014 (extended deadline) Position Paper Authors Notification: November 6, 2014 Regular and Position Paper Camera Ready and Registration: November 17, 2014 - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Dear Christian Wellekens, Let me kindly inform you that due to numerous requests the position paper submission deadline for the International Conference on Bio-inspired Systems and Signal Processing (BIOSIGNALS 2015 - http://www.biosignals.biostec.org/) has been extended to 9 October 2014. We hope you can participate in this prestigious conference by submitting a position paper reflecting your current research in any of the conference topics, which are detailed further below. This conference is part of the 8th International Joint Conference on Biomedical Engineering Systems and Technologies - BIOSTEC (http://www.biostec.org/) and it is co-located with four related conference, namely: - BIODEVICES - International Conference on Biomedical Electronics and Devices (http://www.biodevices.biostec.org/) - BIOIMAGING - International Conference on Bioimaging (http://www.bioimaging.biostec.org/) - BIOINFORMATICS - International Conference on Bioinformatics Models, Methods and Algorithms (http://www.bioinformatics.biostec.org/) - HEALTHINF - International Conference on Health Informatics (http://www.healthinf.biostec.org/) Registration to one conference allows free access to all other BIOSTEC conferences. The conference will be sponsored by the Institute for Systems and Technologies of Information, Control and Communication (INSTICC), held in cooperation with the EUROMICRO, International Society for Telemedicine & eHealth (ISfTeH) and Association for the Advancement of Artificial Intelligence (AAAI) and has a technical co-sponsorship by the Biomedical Engineering Society (BMES), European Society for Engineering and Medicine (ESEM) and IEEE Engineering in Medicine and Biology Society (IEEE EMBS). INSTICC is Member of the Workflow Management Coalition (WfMC), Object Management Group (OMG) and Foundation for Intelligent Physical Agents (FIPA). The BMC Medical Informatics and Decision Making will be the Media Partner and the Science and Technology Events (SCITEVENTS) the Logistics Partner. BIOSIGNALS is interested in promoting high quality research as it can be confirmed by last year acceptance rates, where from 70 submissions, 20% were presented as full papers. We would like to highlight the presence of the following keynote speakers: - Erik Meijering, Erasmus University Medical Center, Netherlands - Lionel Pazart, CHU, France - Nuno Sousa, University of Minho, Portugal - David Rose, MIT Media Lab, United States Submitted papers will be subject to a double-blind review process. All accepted papers will be published in the conference proceedings, under an ISBN reference, on paper and on CD-ROM support. It is planned to publish a short list of revised and extended versions of presented papers with Springer in a CCIS Series book. The proceedings will be submitted for indexation by Thomson Reuters Conference Proceedings Citation Index (ISI), INSPEC, DBLP, EI (Elsevier Index) and Scopus. All papers presented at the conference venue will be available at the SCITEPRESS Digital Library (http://www.scitepress.org/DigitalLibrary/). SCITEPRESS is a member of CrossRef (http://www.crossref.org/). Special Sessions: - Multivariable Processing for Biometric Systems – MPBS 2015 (http://www.biosignals.biostec.org/MPBS.aspx) - BEyond SPeech Acoustics: Enhancing Communication through Non-acoustic Signals – BESPA 2015 (http://www.biosignals.biostec.org/BESPA.aspx) Tutorials: - From Analysis Pipelines to Biological Insights from ChIP Sequencing Data - Big Data Analytics in Biomedical Informatics Best paper awards will be distributed during the conference closing session. Please check the website for further information (http://www.biosignals.biostec.org/BestPaperAward.aspx). Workshops, Special sessions, Tutorials as well as Demonstrations dedicated to other technical/scientific topics are also envisaged: companies interested in presenting their products/methodologies or researchers interested in holding a tutorial are invited to contact the conference secretariat. Workshop chairs and Special Session chairs will benefit from logistics support and other types of support, including secretariat and financial support, to facilitate the development of a valid idea. Finally, we also would like to highlight the Doctoral Consortium on Biomedical Engineering Systems and Technologies that will take place in conjunction with BIOSTEC and aims to provide an opportunity for graduate students to explore their research interests in an interdisciplinary workshop, under the guidance of a panel of distinguished experts in the field (http://www.biostec.org/DoctoralConsortium.aspx). Please check further details at the BIOSIGNALS conference website (http://www.biosignals.biostec.org/). Should you have any question please don't hesitate contacting me. Kind regards, Claudia Pinto On behalf of BIOSIGNALS Secretariat Av. D. Manuel I, 27A 2.Esq. 2910-595 Setubal, Portugal Tel.: +351 265 100 033 Fax: +44 203 014 8813 Email: biosignals.secretariat@insticc.org - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - CONFERENCE CO-CHAIRS: Ana Fred, Instituto de Telecomunicacoes / IST, Portugal Hugo Gamboa, CEFITEC / FCT - New University of Lisbon, Portugal Dirk Elias, University of Porto / Fraunhofer, Portugal PROGRAM CHAIR: Harald Loose, Brandenburg University of Applied Sciences, Germany PROGRAM COMMITTEE: Please check the program committee members at http://www.biosignals.biostec.org/ProgramCommittee.aspx CONFERENCE TOPICS: - Speech Recognition - Neural Networks - Biometrics - Pattern Recognition - Medical Signal Acquisition, Analysis and Processing - Wearable Sensors and Systems - Real-Time Systems - Evolutionary Systems - Acoustic Signal Processing - Time and Frequency Response - Wavelet Transform - Medical Image Detection, Acquisition, Analysis and Processing - Physiological Processes and Bio-signal Modeling, Non-linear dynamics - Cybernetics and User Interface Technologies - Electromagnetic fields in biology and medicine - Fuzzy Systems and Signals - Monitoring and Telemetry - Cardiovascular Signals - Image Analysis and Processing - Detection and Identification - Motion Control
| |||||||||||||||||||||||||
3-3-16 | (2015-03-02) LATA 2015 (extended submission deadline)LATA 2015 Nice, France March 2-6, 2015 Organized by: CNRS, I3S, UMR 7271 Nice Sophia Antipolis University Research Group on Mathematical Linguistics (GRLMC) Rovira i Virgili University http://grammars.grlmc.com/lata2015/ **************************************************************************************** AIMS: LATA is a conference series on theoretical computer science and its applications. Following the tradition of the diverse PhD training events in the field developed at Rovira i Virgili University in Tarragona since 2002, LATA 2015 will reserve significant room for young scholars at the beginning of their career. It will aim at attracting contributions from classical theory fields as well as application areas. VENUE: LATA 2015 will take place in Nice, the second largest French city on the Mediterranean coast. The venue will be the University Castle at Parc Valrose. SCOPE: Topics of either theoretical or applied interest include, but are not limited to: algebraic language theory algorithms for semi-structured data mining algorithms on automata and words automata and logic automata for system analysis and programme verification automata networks automata, concurrency and Petri nets automatic structures cellular automata codes combinatorics on words computational complexity data and image compression descriptional complexity digital libraries and document engineering foundations of finite state technology foundations of XML fuzzy and rough languages grammars (Chomsky hierarchy, contextual, unification, categorial, etc.) grammatical inference and algorithmic learning graphs and graph transformation language varieties and semigroups language-based cryptography parallel and regulated rewriting parsing patterns power series string and combinatorial issues in bioinformatics string processing algorithms symbolic dynamics term rewriting transducers trees, tree languages and tree automata unconventional models of computation weighted automata STRUCTURE: LATA 2015 will consist of: invited talks invited tutorials peer-reviewed contributions INVITED SPEAKERS: to be announced PROGRAMME COMMITTEE: Andrew Adamatzky (West of England, Bristol, UK) Andris Ambainis (Latvia, Riga, LV) Franz Baader (Dresden Tech, DE) Rajesh Bhatt (Massachusetts, Amherst, US) José-Manuel Colom (Zaragoza, ES) Bruno Courcelle (Bordeaux, FR) Erzsébet Csuhaj-Varjú (Eötvös Loránd, Budapest, HU) Aldo de Luca (Naples Federico II, IT) Susanna Donatelli (Turin, IT) Paola Flocchini (Ottawa, CA) Enrico Formenti (Nice, FR) Tero Harju (Turku, FI) Monika Heiner (Brandenburg Tech, Cottbus, DE) Yiguang Hong (Chinese Academy, Beijing, CN) Kazuo Iwama (Kyoto, JP) Sanjay Jain (National Singapore, SG) Maciej Koutny (Newcastle, UK) Antonín Kučera (Masaryk, Brno, CZ) Thierry Lecroq (Rouen, FR) Salvador Lucas (Valencia Tech, ES) Veli Mäkinen (Helsinki, FI) Carlos Martín-Vide (Rovira i Virgili, Tarragona, ES, chair) Filippo Mignosi (L’Aquila, IT) Victor Mitrana (Madrid Tech, ES) Ilan Newman (Haifa, IL) Joachim Niehren (INRIA, Lille, FR) Enno Ohlebusch (Ulm, DE) Arlindo Oliveira (Lisbon, PT) Joël Ouaknine (Oxford, UK) Wojciech Penczek (Polish Academy, Warsaw, PL) Dominique Perrin (ESIEE, Paris, FR) Alberto Policriti (Udine, IT) Sanguthevar Rajasekaran (Connecticut, Storrs, US) Jörg Rothe (Düsseldorf, DE) Frank Ruskey (Victoria, CA) Helmut Seidl (Munich Tech, DE) Ayumi Shinohara (Tohoku, Sendai, JP) Bernhard Steffen (Dortmund, DE) Frank Stephan (National Singapore, SG) Paul Tarau (North Texas, Denton, US) Andrzej Tarlecki (Warsaw, PL) Jacobo Torán (Ulm, DE) Frits Vaandrager (Nijmegen, NL) Jaco van de Pol (Twente, Enschede, NL) Pierre Wolper (Liège, BE) Zhilin Wu (Chinese Academy, Beijing, CN) Slawomir Zadrozny (Polish Academy, Warsaw, PL) Hans Zantema (Eindhoven Tech, NL) ORGANIZING COMMITTEE: Sébastien Autran (Nice) Adrian Horia Dediu (Tarragona) Enrico Formenti (Nice, co-chair) Sandrine Julia (Nice) Carlos Martín-Vide (Tarragona, co-chair) Christophe Papazian (Nice) Julien Provillard (Nice) Pierre-Alain Scribot (Nice) Bianca Truthe (Giessen) Florentina Lilica Voicu (Tarragona) 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, 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://www.easychair.org/conferences/?conf=lata2015 PUBLICATIONS: A volume of proceedings published by Springer in the LNCS 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 period for registration is open from July 21, 2014 to March 2, 2015. The registration form can be found at: http://grammars.grlmc.com/lata2015/Registration.php DEADLINES: Paper submission: October 16, 2014 (23:59 CET) (extended) Notification of paper acceptance or rejection: November 18, 2014 Early registration: November 25, 2014 Final version of the paper for the LNCS proceedings: November 26, 2014 Late registration: February 16, 2015 Submission to the journal special issue: June 6, 2015 QUESTIONS AND FURTHER INFORMATION: florentinalilica.voicu@urv.cat POSTAL ADDRESS: LATA 2015 Research Group on Mathematical Linguistics (GRLMC) Rovira i Virgili University Av. Catalunya, 35 43002 Tarragona, Spain Phone: +34 977 559 543 Fax: +34 977 558 386 ACKNOWLEDGEMENTS: Nice Sophia Antipolis University Rovira i Virgili University
| |||||||||||||||||||||||||
3-3-17 | (2015-05-07) 3rd International Conference on Learning Representations (ICLR2015), San Diego, USA -------------------------------------------------------------------
| |||||||||||||||||||||||||
3-3-18 | (2015-05-28) International Conference for Young Researchers in Linguistics, Toulouse, France (extended deadline) International Conference for Young Researchers in Linguistics
Discourse(s) In Linguistics: Units and Levels of Analysis
May 28th and 29th 2015 Toulouse - France www.jetou2015.fr
Submission Deadline: Friday October 24th 2014 EXTENDED Call for Papers
The doctoral students in Linguistics of the laboratories at Toulouse University, France:
CLLE-ERSS (Équipe de Recherche en Syntaxe et Sémantique) IRIT (Institut de Recherche en Informatique de Toulouse) OCTOGONE-Lordat (Centre Interdisciplinaire des Sciences du Langage et de la Cognition)
are organizing the 5th edition of JéTou (Journées d'études Toulousaines), an international conference aiming at gathering doctoral students and young researchers (who have defended their dissertation within the past three years) together, from the different disciplines of Linguistics, on an open and multidisciplinary theme.
This 2015 edition will be devoted to a reflection on the following theme: “Discourse(s) in Linguistics: Units and Levels of Analysis”.
The term discourse, understood in its broadest sense as a multimodal language production (oral, written, verbal, gestural) is at the heart of Linguistics. Both in production and reception, investigation methods have led to analysis levels with variable granularities, where overlapping units maintain relationships with strong interdependence. Therefore, discourse depends on both the object and the meaning given to it.
Common issues are: planning, segmentation, organization, modeling. A valuable reflection involving different fields arises from these challenges; more than ever, an interdisciplinary practice is necessary to further the various aspects of discourse.
Research in these fields has taken different forms. Besides, the gap between theoretical models and empirical studies based on real data has been significantly reduced in the last few years. Qualitative as well as quantitative, these works have raised new questions: choice of units, collection and annotation of corpora, evaluation procedures, comparison and interpretation of results, etc.
This edition will focus mainly on levels of analysis and units in discourse. Possible topics include:
Obviously, this list does not include all the research possibilities following from the theme of the conference, which is why every submission that addresses the notions of discourse in the Language Sciences will be read and reviewed. Proposals which include theoretical reflections and actual data will be particularly appreciated.
JéTou 2015 offers a challenging theme that every field of Language Sciences can adapt for themselves. This conference will give the opportunity, to those who wish to come, to ask questions, discuss and compare their work, their methods, their reflections in an interdisciplinary context, which favours positive interactions and constructive debates.
Guest Speakers :
Submission Guidelines:
Articles must be written in French or English.
Submissions must not exceed 3 pages for an oral presentation as well as for a scientific poster (references included). These three pages must include a title, a summary and up to 5 keywords (letter type: Times New Roman 12, simple spacing, normal margin). You can indicate by email your preference for an oral presentation (20 min + 10 min for questions) or for a scientific poster, but the final decision on the format of the presentation will be made by the organization committee alone.
Papers should be submitted via the EasyChair conference system: https://www.easychair.org/conferences/?conf=jtou2015
The conference proceedings will be published and given to the participants (5 pages for a scientific poster and 10 pages for an oral presentation).
Selection Criteria
Each submission will be reviewed by at least two experts in the relevant field. The following elements will be considered:
. in the field.
Schedule
Deadline for submission of summaries: Friday October 10th 2014, Notification of acceptance: Friday November 21st 2014, Submission deadline for long papers: Friday January 16th 2015, Submission deadline for final versions: Friday April 10th 2015,
Conference: Thursday May 28th and Friday May 29th 2015 at Université Toulouse - Jean Jaurès (Mirail campus).
Organising Committee
Francesca Cortelazzo, Jean-Philippe Fauconnier, Laury Garnier, Luce Lefeuvre, Sophie Mayras-Cauchois, Olivier Nocaudie, Florian Savreux, Maxime Warnier.
Website www.jetou2015.fr Contact contact.jetou2015@gmail.com
| |||||||||||||||||||||||||
3-3-19 | (2015-06-22) Conférence TALN 2015 | RÉCITAL 2015, Caen, France Conférence TALN 2015 | RÉCITAL 2015
| |||||||||||||||||||||||||
3-3-20 | (2015-08-26) LVA 2015 - 12th International Conference on Latent Variable Analysis and Signal Separation
LVA 2015 - 12th International Conference on Latent Variable Analysis and Signal Separation August 24-26, 2015, Liberec, Czech Republic http://amca.cz/lva2015/ *About LVA* LVA 2015 will be the 12th in a series of international conferences which attracted hundreds of researchers and practitioners over the years. Since its start in 1999 under the banner of Independent Component Analysis and Blind Source Separation (ICA), the conference has continuously broadened its horizons. It encompasses today a host of additional forms and models of general mixtures of latent variables. Theories and tools borrowing from the fields of signal processing, applied statistics, machine learning, linear and multilinear algebra, numerical analysis and optimization, and numerous application fields offer exciting interdisciplinary interactions. *Highlights* The conference will be preceded by a Summer School on Latent Variable Analysis and Signal Separation and it will feature the much-awaited results of the 5th Signal Separation Evaluation Campaign (SiSEC 2015).Keynote talks will be given by three leading researchers:- Tülay Adali (University of Maryland, Baltimore County, USA)- Rémi Gribonval (Inria, France)- DeLiang Wang (Ohio State University, USA) *Call for Papers* The proceedings will be published in Springer-Verlag's Lecture Notes in Computer Science Series (LNCS). Prospective authors are invited to submit original papers (up to 8 pages in LNCS format) in areas related to latent variable analysis and signal separation, including but not limited to:- Theory: sparse coding, dictionary learning; statistical and probabilistic modeling; detection, estimation and performance criteria and bounds; causality measures; learning theory; convex/nonconvex optimization tools- Models: general linear or nonlinear models of signals and data; discrete, continuous, flat, or hierarchical models; multilinear models; time-varying, instantaneous, convolutive, noiseless, noisy, over-complete, or under-complete mixtures- Algorithms: estimation, separation, identification, detection, blind and semi-blind methods, non-negative matrix factorization, tensor decomposition, adaptive and recursive estimation; feature selection; time-frequency and wavelet based analysis; complexity analysis- Applications: speech and audio separation, recognition, dereverberation and denoising; auditory scene analysis; image segmentation, separation, fusion, classification, texture analysis; biomedical signal analysis, imaging, genomic data analysis, brain-computer interface- Emerging related topics: sparse learning; deep learning; social networks; data mining; artificial intelligence; objective and subjective performance evaluation. *Special Sessions* The program will also feature special sessions on new or emerging topics of interest. Proposals for special sessions must include the session title, rationale, outline, and a list of 4 to 6 invited papers. To submit, see http://amca.cz/lva2015/. *Important Dates*
*Organizing Committee* General chairs:Zbynek Koldovsky (Technical University of Liberec, Czech Republic)Petr Tichavsky (Academy of Sciences, Czech Republic)Program chairs:Arie Yeredor (Tel-Aviv University, Israel)Emmanuel Vincent (Inria, France)Special sessions: Shoji Makino (University of Tsukuba, Japana)SiSEC chair: Nobutaka Ono (NII, Japan)Overseas liaison: Andrzej Cichocki (RIKEN, Japan)
| |||||||||||||||||||||||||
3-3-21 | (2015-08-31) Joint Conference PEVOC & MAVEBA 2015, Firenze, Italia Joint Conference PEVOC & MAVEBA 2015: August 31 - September 4, 2015, Palazzo degli Affari, Piazza Adua 1, Firenze, Italy
| |||||||||||||||||||||||||
3-3-22 | (2015-09-04) Workshop on Speech and Language Technology for Education (SLaTE 2015) Workshop on Speech and Language Technology for Education (SLaTE 2015) Satellite event of Interspeech 2015 Leipzig,Germany The ISCA (International Speech Communication Association) Special Interest Group (SIG) on Speech and Language Technology in Education (SLaTE) promotes the use of speech and language technology for educational purposes, and provides a forum for exchanging information regarding recent developments and other matters of interest related to this topic. For further information please visit http://www.sigslate.org. The upcoming Sixth Workshop on Speech and Language Technologies for Education (SLaTE 2015) will be organized by the Pattern Recognition Lab of Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) in cooperation with Hochschule für Telekommunikation Leipzig (HfTL). The workshop will be held in Leipzig, September 4–5, 2015. It is a satellite event of the 16th Annual Conference of the International Speech Communication Association (INTERSPEECH 2015), which will take place afterwards in Dresden, September 6–10, 2015. Dresden is only 120 km away from Leipzig and can be reached easily within 72 minutes by train (ICE). If you are interested, please download our flyer or our posters (poster 1 and poster 2). We will present them at the INTERSPEECH 2015 booth at INTERSPEECH 2014 in Singapore. We are looking forward to welcome you in Leipzig!
| |||||||||||||||||||||||||
3-3-23 | (2015-09-05) Workshop on the History of Speech Communication, Dresden, Germany Workshop on the History of Speech Communication, (Sig-Hist) Technische Sammlungen, Dresden, Germany Organizers: Rüdiger Hoffmann ruediger.hoffmann@tu-dresden.de Jürgen Trouvain trouvain@coll.uni-saarland.de
| |||||||||||||||||||||||||
3-3-24 | (2015-10-12) CfP 6th International Conference Information Systems and Economic Intelligence: special session: structuring multimedia streams
CALL FOR PAPERS SIIE ̓ 2015 6th edition of the International Conference Information Systems and Economic Intelligence February 12-14th., 2015 in Hammamet (Tunisia) (http://siie2015.loria.fr) Special session: structuring multimedia streams More and more documents and multimedia streams are available on the web. To exploit these extremely large and heterogeneous data, it is necessary to index or to annotate. This task cannot be done manually. We must therefore automatically segment, transcribe, classify, extract keywords and named entities, such as personal names, company names or place names. The results of these treatments provide a structured multimedia stream. These data will be very profitable for individuals, corporations and government agencies. This special session focuses on different methodologies for structuring multimedia streams. Important Dates: Paper submissions (deadline): November 15th, 2014 Notification to authors: December 20th, 2014 Final version for accepted papers: January 5th, 2015
Paper Formats (DOC, RTF or PDF):
– Long papers (for completed research): must not exceed 15 pages.
– Short papers (for R&D research and state of the art, for professionals): must not exceed 8 pages.
Languages of the conference: - Paper: all papers must be written in English - Data show: all video projection (PowerPoint) must be written in English - Presentation: oral presentations and discussions are permitted in English and/or in French.
– We invite you to submit your contributions from the site EasyChair Conference System: https://easychair.org/conferences/?conf=siie2015. Organizers of this special session: Irina Illina and Dominique Fohr (LORIA/INRIA, France)
| |||||||||||||||||||||||||
3-3-25 | (2015-12-13) Calls for Challenge Task Proposals ASRU 2015, Scottsdale, Az, USA ASRU 2015 welcomes proposals for challenge tasks. In a challenge task, participants compete or collaborate to accomplish a common or shared task. The results of the challenge will be presented at the ASRU workshop event in the form of papers reporting the achievements of the participants, individually and/or as a whole. We invite organizers to concretely propose such challenge tasks in the form of a 1-2 page proposal. The proposal should include a description of ● the task and its intended goal ● the task organizers and key contact people for the various aspects of the task ● the data or shared resource that is to be used ○ Details on the availability or its collection process ○ Required labeling or other pre-processing and the expected timeline of this process ○ Privacy concerns around the data or resource as it will be released to all participants ○ Licensing terms or conditions for participants ● the evaluation process, how will a test set be defined, what figure of merit will be used to ● measure success, and how will a common scoring process be put in place to arrive at ● comparable results for all participants ● the timeline; when will training/test material be made available, when are participant (sub-)system submissions due ● the expected (number of) participants, and whether this is a new installment of an existing challenge or a new challenge series altogether ● any special requests or circumstances, e.g., required timing or format of the challenge execution Participants will report their achievements in the form of regular format paper submissions to the ASRU workshop. These submissions will undergo the normal ASRU review process, but the organizers can suggest reviewers that would be particularly insightful for the challenge subject matter. Accepted papers will be organized in a special session at the conference (in poster format; the only format used at ASRU). The accepted papers will appear in the ASRU proceedings. Given the possibly lengthy process of organizing and executing a special challenge, prospective organizers are encouraged to submit proposals as soon as possible. The ASRU technical program committee will make acceptance decisions based on a rolling schedule -- i.e., proposals are reviewed as soon as they come in. Challenge proposals should be sent to Technical Program co-chair Michiel Bacchiani at michiel@google.com, and will be accepted until the end of 2014.
| |||||||||||||||||||||||||
3-3-26 | (2016-00-00) Bids invitation for the conference Speech Prosody 2016 (SProSIG)The Advisory Board of SProSIG, the Speech Prosody Special Interest Group, invites bids from sites interested in hosting its flagship conference Speech Prosody in 2016. The bid process will proceed as follows: (1) Optional: Groups interested in hosting a bid are invited to express interest in an e-mail to the current SProSIG Secretary and/or President (e.g., by replying to this e-mail). (2) Optional: Each group interested in hosting the conference is invited to give a presentation on May 23, 2014 at the Speech Prosody 2014 conference in Dublin. (3) Required: Each bid should then be formalized in a written document, mailed to the secretary of SProSIG by June 15, 2014. These documents will be posted at sprosig.isle.illinois.edu for all SProSIG members to read. (4) Selection of the site for Speech Prosody 2016 will then be conducted using an on-line ballot at http://sprosig.isle.illinois.edu. Each current member of SProSIG will be allowed to vote. Bids to host Speech Prosody 2016 should include the following information: (a) Names and affiliations of members of the organizing committee. (b) Information about institutional support for the conference if any. (c) Tentative location of the conference (city and, if possible, venue). Oral and written presentation of the bid should highlight attributes that make both city and site suitable for hosting an international conference, including transportation to/from and within the city, lodging and dining options near the proposed venue, facilities in the proposed venue for a 300-person oral session and a 40-poster poster session, and any other attributes likely to be of interest to the members of SProSIG. (d) Tentative dates of the proposed conference (typically four days in late May 2016) (e) Proposed theme of the conference and/or proposed new session topics that will be included, along with existing session topics of the Speech Prosody conference, in the Conference Call for Papers.
| |||||||||||||||||||||||||
3-3-27 | (2016-00-00) Speech Prosody Boston, USASpeech Prosody 2016 will be held in Boston, USA. Congratulations to Dr. Veilleux, Dr. Barnes, Dr. Shattuck-Hufnagel and Alejna Brugos for presenting an outstanding bid, and we look forward to an outstanding conference in Boston in 2016!
| |||||||||||||||||||||||||
3-3-28 | Announcing the Master of Science in Intelligent Information Systems Carnegie Mellon University
degree designed for students who want to rapidly master advanced content-analysis, mining, and intelligent information technologies prior to beginning or resuming leadership careers in industry and government. Just over half of the curriculum consists of graduate courses. The remainder provides direct, hands-on, project-oriented experience working closely with CMU faculty to build systems and solve problems using state-of-the-art algorithms, techniques, tools, and datasets. A typical MIIS student completes the program in one year (12 months) of full-time study at the Pittsburgh campus. Part-time and distance education options are available to students employed at affiliated companies. The application deadline for the Fall 2013 term is December 14, 2012. For more information about the program, please visit http://www.lti.cs.cmu.edu/education/msiis/overview.shtml
| |||||||||||||||||||||||||
3-3-29 | CALL FOR PROPOSALS ICASSP 2019 ICASSP 2019
The IEEE Signal Processing Society is accepting proposals for the 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP®). SPS Members are invited to submit a proposal to host ICASSP. If you are interested in submitting a proposal please contact Nicole Allen to get the forms and guidelines. ICASSP is the world’s largest and most comprehensive technical conference focused on signal processing applications. The series is sponsored by the IEEE Signal Processing Society and has been held annually since 1976. The conference features world-class speakers, tutorials, exhibits, and over 120 lecture and poster sessions. ICASSP is a cooperative effort of the IEEE Signal Processing Technical Committees:
To submit a proposal, send a notice of intent to bid to the Vice President – Conferences and the Conference Service Coordinator using the email addresses as shown below. Include in the notice your contact information and the proposed location. The Signal Processing Society Conference Services staff will issue the proposal submission form and guidlines upon receipt of the letter of intent. The form must be completed and the proposal submitted to the Conference Services staff by 21 March 2014. Proposals will be assessed by the Conference Board Executive Subcommittee. Accepted bidding teams [finalists] will be invited to present at the Conference Board meeting held at ICASSP 2014, May 4-9, 2014 in Florence, Italy.
| |||||||||||||||||||||||||
3-3-30 | Master in linguistics (Aix-Marseille) France Master's in Linguistics (Aix-Marseille Université): Linguistic Theories, Field Linguistics and Experimentation TheLiTEx offers advanced training in Linguistics. This specialty focuses Linguistics is aimed at presenting in an original way the links between corpus linguistics and scientific experimentation on the one hand and laboratory and field methodologies on the other. On the basis of a common set of courses (offered within the first year), TheLiTEx offers two paths: Experimental Linguistics (LEx) and Language Contact & Typology (LCT) The goal of LEx is the study of language, speech and discourse on the basis of scientific experimentation, quantitative modeling of linguistic phenomena and behavior. It focuses on a multidisciplinary approach which borrows its methodologies to human physical and biological sciences and its tools to computer science, clinical approaches, engineering etc.. Among the courses offered: semantics, phonetics / phonology, morphology, syntax or pragmatics, prosody and intonation, and the interfaces between these linguistic levels, in their interactions with the real world and the individual, in a biological, cognitive and social perspective. Within the second year, a set of more specialized courses is offered such as Language and the Brain and Laboratory Phonology. LCT aims at understanding the world's linguistic diversity, focusing on language contact, language change and variation (European, Asian and African languages, Creoles, sign language, etc.).. This specialty focuses, from a a linguistic and sociolinguistic perspective, on issues of field linguistics and taking into account both the human and socio-cultural dimension of language (speakers, communities). It also focuses on documenting rare and endangered languages and to engage a reflection on linguistic minorities. This path also provides expertise and intervention models (language policy and planning) in order to train students in the management of contact phenomena and their impact on the speakers, languages and societies More info at: http://thelitex.hypotheses.org/678
| |||||||||||||||||||||||||
3-3-31 | NEW MASTER IN BRAIN AND COGNITION AT UNIVERSITAT POMPEU FABRA, BARCELONA NEW MASTER IN BRAIN AND COGNITION AT UNIVERSITAT POMPEU FABRA, BARCELONA
| |||||||||||||||||||||||||
3-3-32 | Research in Interactive Virtual Experiences at USC CA USA REU Site: Research in Interactive Virtual Experiences --------------------------------------------------------------------
The Institute for Creative Technologies (ICT) offers a 10-week summer research program for undergraduates in interactive virtual experiences. A multidisciplinary research institute affiliated with the University of Southern California, the ICT was established in 1999 to combine leading academic researchers in computing with the creative talents of Hollywood and the video game industry. Having grown to encompass a total of 170 faculty, staff, and students in a diverse array of fields, the ICT represents a unique interdisciplinary community brought together with a core unifying mission: advancing the state-of-the-art for creating virtual reality experiences so compelling that people will react as if they were real.
Reflecting the interdisciplinary nature of ICT research, we welcome applications from students in computer science, as well as many other fields, such as psychology, art/animation, interactive media, linguistics, and communications. Undergraduates will join a team of students, research staff, and faculty in one of several labs focusing on different aspects of interactive virtual experiences. In addition to participating in seminars and social events, students will also prepare a final written report and present their projects to the rest of the institute at the end of summer research fair.
Students will receive $5000 over ten weeks, plus an additional $2800 stipend for housing and living expenses. Non-local students can also be reimbursed for travel up to $600. The ICT is located in West Los Angeles, just north of LAX and only 10 minutes from the beach.
This Research Experiences for Undergraduates (REU) site is supported by a grant from the National Science Foundation. The site is expected to begin summer 2013, pending final award issuance.
Students can apply online at: http://ict.usc.edu/reu/ Application deadline: March 31, 2013
For more information, please contact Evan Suma at reu@ict.usc.edu.
|