Keywords

Co-authors

Social networks

Export Publications

Export the displayed publications:
Number of documents

121

Frederic Bechet


Summary

Frédéric Béchet is a researcher in the field of Speech and Natural Language Processing at the Laboratoire d'Informatique Fondamentale (LIF) of Marseille.

After studying Computer Science at the Aix-Marseille II University, he obtained his PhD in Computer Science in 1994 from the University of Avignon, France. Since then he worked at the Ludwig Maximilian University in Munich, Germany, as a Professor Assistant at the University of Avignon, France, as an invited professor at AT&T Research Shannon Lab in Florham Park, New Jersey, USA.

He is currently a full Professor of Computer Science at the Aix Marseille Université in France since 2009.

In terms of managerial activities, Frédéric Béchet is currently at the head of the Computer Science Research Federation of the Aix Marseille University (Fédération de Recherche en Informatique et Interactions d’Aix-Marseille, FRIIAM - FR3513).

Research activities

My research activities are focused on automatic language processing models for Spoken Language Understanding. By dealing with spoken language, I’m working at the crossing of Natural Language Processing on one hand and Automatic Speech Recognition on the other hand.

The main research topics that I studied during my academic career are :

  • Language modelling for speech processing ;
  • Spoken Language Understanding ;
  • Spoken Dialog systems ;
  • Robust syntactic/semantic parsing.

 

These topics have been studied through three applicative frameworks: automatic spoken dialog systems; speech analytics; linguistic processing of non-canonical texts. One focus of my work is to combine academic research to applicative frameworks defined through collaborative projects with industrial partners. These projects are a unique opportunity to work on large "realistic" datasets in order to develop and evaluate new language processing models. These models are mostly corpus-based models with various machine learning methods integrating linguistically motivated resources.

Carreer

After studying Computer Science at the University of Marseille I obtained my PhD in 1994 at the University of Avignon with Professor Henri Meloni on Language Processing for Automatic Speech Recognition.

After this PhD I did a post-doctoral research contract of 16 months at the Computational Linguistics Laboratory (CIS) of the Ludwig Maximilian University of Munich, Germany. This experience allowed me to precise the line of research I still follow today, at the intersection of Natural Language Processing one hand, and Speech Processing on the other hand.

I obtained a Professor Assistant position at the University of Avignon in September 1995. I joined Professor de Mori team, working on speech processing for Spoken Dialog Systems.

I went on a sabbatical leave for one year in 2001 which I spent as an Invited Professor at the AT&T Shannon Labs in New Jersey, USA. I worked in Allan Gorin team on the Spoken Dialog System “How May I Help You?”.

 

I obtained my « habilitation à diriger des recherches » in 2007 and a Full Professor position at the Aix Marseille University in 2009. I joined the NLP team of the Laboratoire d’Informatique Fondamentale (LIF).

My first area of research, during my PhD, was the application of analytical models, knowledge based, for Automatic Speech Recognition. Former student of Alain Colmerauer, this line of work was very influenced by logic programming, inference and Artificial Intelligence. After my PhD I started working with machine learning corpus-based approaches for speech processing.

 

Since my arrival in the Natural Language Processing team (TALEP) of the Computer-Science lab (LIF) of Marseille, I work on the combination of efficient Machine Learning approaches with rich linguistic resources. During these 5 past years I have been interested in multimodal approaches language processing. By considering language in several modalities (image, audio, text), I try to combine through joint processing different analyses that can be done in a multimodal document such as a video.

 

Full CV

Work Experience

  • 1993-1994 Post-doctoral research contract at the Computational Linguistics lab (CIS – Center für Information und Sprachverarbeitung) of the Ludwig Maximilians University of Munich, Germany
  • 1994-2009 Research assistant at the University of Avignon, France
  • 2001-2002 Invited Professor at the AT&T Shannon Lab, Florham Park, New Jersey, USA
  • since 2009 Full University Professor at the Aix Marseille University, France

 

Main research domains

  • Natural Language Processing
  • Automatic Speech Recogntion

Main teaching activities

  • Algorithmic and Programmation
  • Compilation
  • Natural Language Processing

 

Administrative responsibilities

  • Head of the Computer Science Research Federation of the Aix Marseille University (Fédération de Recherche en Informatique et Interactions d’Aix-Marseille, FRIIAM - FR3513)
  • Head of the cursus "Multimedia Information Retrieval" of the computer science Master degree of the Aix Marseille University
  • Board member of the Computer Science departement of the Aix Marseille University
  • Board member of the Mathematics and Computer Science doctoral studies of the Aix Marseille University

 

Research contracts

  • Participation to international programs : 3 European projects, 2 networks of excellence, 1 US funded project (DARPA)
  • Participation to 8 French ANR projects depuis 2007 (Principal Investigator of 3 of them)
  • Participation to industrial projects with France Télécom Orange Labs Pattents
  • 2 US patterns produced while at AT&T Shannon Labs in 2001/2002

 

Research dissemination

  • Vice-president (since 2012) of the French Natural Language Processing scientific association (Association pour le traitement automatique des langues - ATALA)
  • Elected member (2008-2010) of the IEEE Signal Processing Society Speech and Language Technical Committee
  • Associate editor for IEEE Signal Processing Letter since 2012
  • Organisation of conferences : co-chair of JEP-TALN2008, SLAM 2013, TALN 2014 ; area-chair for Interspeech 2012, SLT 2012 ; member of the organizing comittee of Interspeech 2013
  • Reviewer for scientific journals : Speech Communication, IEEE Signal Processing Letters, IEEE Transactions on Speech and Audio Processing, ATALA TAL
  • Member of reviewing committee : ICASSP, Interspeech, Eusipco, IEEE ASRU, Human Language Technology, Empirical Method Natural Language Processing, ACL/IEEE SLT, AFCP JEP, ATALA TALN.
  • Participation to experts panels (AERES, INRIA, ANR, European projects)

 

PhD supervision

  • Supervisor or co-supervisor of 14 PhD programs since 2002
  • Currently supervising 4 PhD students

 

Career

Frédéric Béchet is a researcher in the field of Speech and Natural Language Processing. His research activities are mainly focused on Spoken Language Understanding for both Spoken Dialogue Systems and Speech Mining applications. After studying Computer Science at the University of Marseille, he obtained his PhD in Computer Science in 1994 from the University of Avignon, France. Since then he worked at the Ludwig Maximilian University in Munich, as a Professor Assistant at the University of Avignon, as an invited professor at ATT Research Shannon Lab in Florham Park, New Jersey.

Frédéric Béchet is currently a full Professor of Computer Science at the Aix Marseille University, and a member of the Natural Language Processing research group of the Laboratoire d’Informatique de Marseille (LIF-CNRS).

Frédéric Béchet is the author/co-author of over 100 refereed papers in journals and international conferences and hold two patents.

He is an Associate Editor for IEEE Signal Processing Letter since 2012, has served on the reviewing committees of several international conferences (ICASSP, Interspeech, ASRU, HLT, EMNLP) and has been an invited reviewer for several journals including : Speech Communication, IEEE Signal Processing Letters, IEEE Transactions on Speech and Audio Processing, Traitement Automatique des Langues.

Frédéric Béchet was an elected member of the IEEE Speech and Language Processing Technical Committee and is currently vice-president of the board of the French Natural Language Processing association ATALA.

Frédéric Béchet has been involved in many French and European research programs in the fields of Speech Processing and Spoken Dialog Systems : FP5 SMADA STREP, FP6 LUNA STREP, FP6 PASCAL NoE, ANR EPAC, ANR SEQUOIA, ANR EDYLEX, ANR DECODA, ANR PERCOL, ANR ASFALDA, ANR ORFEO, ANR DATCHA.

He was the Coordinator of several French programs such as PERCOL, DECODA and DATCHA, as well as Principal Investigator for the Aix Marseille University for a US DARPA funded project (BOLT 2012-2015).

In terms of managerial activities, Frédéric Béchet is currently at the head of the Computer Science Research Federation of the Aix Marseille University (Fédération de Recherche en Informatique et Interactions d’Aix-Marseille, FRIIAM - FR3513). 3

Scientific activities

My research activities are mainly focused on automatic language processing models for Spoken Language Understanding (SLU). By dealing with spoken language, I’m working at the crossing of Natural Language Processing (NLP) on one hand and Automatic Speech Recognition (ASR) on the other hand.

The main research topics that I studied during my academic career are :

  • Language modeling for speech processing (recognition and synthesis) ;
  • Spoken Language Understanding ;
  • Spoken Dialog systems ;
  • Robust syntactic/semantic parsing.

These topics have been studied through three applicative frameworks: automatic spoken dialog systems; speech analytics ; linguistic processing of non-canonical texts. One focus of my work is to combine academic research to applicative frameworks defined through collaborative projects with industrial partners. These projects are a unique opportunity to work on large "realistic" datasets in order to develop and evaluate new language processing models.

These models are mostly corpus-based models with various machine learning methods integrating linguistically motivated ressources.

Along these lines I have participated to many collaborative projects with international academic partners (e.g. LIMSI and Paris7-Alpage in France; University of Trento, University of Sheffield, RWTH Aachen University in Europe; Columbia University, Washington University in USA) and industrial partners leaders in their fields related to Spoken Language Processing (France-Telecom Orange in France ; Loquendo and Teleperformance in Italy ; AT&T Labs and SRI International in USA).

In addition to these collaborative projects, I have participated to many evaluation programs on a large range of NLP tasks in order to validate the models and methods proposed by comparing them to other teams results, such as :

  • Text-to-Phoneme conversion : French program Technolangue ;
  • Named Entity Recognition from Speech : French programs ESTER and ETAPE;
  • Opinion classification : French program DEFT, SemEval ;
  • Spoken Language Understanding : French program MEDIA, DARPA BOLT project (with Machine Translation) ;
  • Multimodal person recognition: French challenge Defi-REPERE.

 

My current research activities are focused on two main topics: robust linguistic analysis and multimodal language processing, both applied to interactive language.

By interactive language I consider not only spoken dialogs, but also all computer-mediated communication such as chat, comments on blogs, tweets, etc.

My work on Robust linguistic analysis is about the adaptation of parsing models (syntactic, semantic, discourse) to process noisy text either produced by an automatic system (Automatic Speech Recognition or Machine Translation systems) or representing non-canonical language (spontaneous speech, social-media data). The use of linguistically motivated models for performing multi-level parsing, in addition to supervised and unsupervised machine learning methods, aims to provide a generic representation of a message that can be used to perform a large range of language understanding tasks, from

ASR error correction as in the DARPA funded BOLT project (2011-2015) where clarification dialogs are used to correct a message prior to translation, to abstractive summary generation in the European project SENSEI (2014-2016) dedicated to extract knowledge from large archives of spoken and text conversations.

Since my arrival at the Aix Marseille University, in September 2009, I collaborate with the Machine Learning and Multimedia processing team (QARMA) of my lab, leading to an extension of my research areas to multimodal language processing in video documents. This collaboration lead to the participation to the French ANR-DGA scientific challenge REPERE (2010-2014) which was about multimodal person recognition in broadcast video documents. I was the coordinator of a 3-years funded collaborative project with the University of Avignon, the University of Lille and France-Telecom Orange Labs in order to participate to this challenge.

Our consortium was ranked first on the main task at the last 2014 evaluation. My main contribution in this direction of research is to consider the problem as a multimodal understanding problem where the different modalities are integrated as early as possible in the understanding process instead of the standard late fusion approach. In particular scene analysis was integrated into the speaker role recognition process prior to speaker clustering in the person identification process for the REPERE challenge.

 

This work is currently extended through two projects, one funded by the French DGA on multimodal language understanding, the other one funded by the French Intiative of Excellence A*MIDEX on video recommendation.


Journal articles9 documents

  • G. Riccardi, Frédéric Bechet, M. Danieli, B. Favre, R. Gaizauskas, et al.. The SENSEI Project: Making Sense of Human Conversations. Lecture Notes on Artificial Intelligence, 2016, LNAI 9577, pp.10-33. ⟨hal-01454923⟩
  • Rahma Boujelbane, Mariem Ellouze, Frédéric Béchet, Lamia Belguith. De l’arabe standard vers l’arabe dialectal : projection de corpus et ressources linguistiques en vue du traitement automatique de l’oral dans les médias tunisiens. Revue TAL, Association pour le Traitement Automatique des Langues, 2015, pp.rahma-boujelbane. ⟨halshs-01193325⟩
  • Nathalie Camelin, Frederic Bechet, Géraldine Damnati, Renato de Mori. Detection and Interpretation of Opinion Expressions in Spoken Surveys. IEEE Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2010, ⟨10.1109/TASL.2009.2028918⟩. ⟨hal-01314505⟩
  • Thierry Bazillon, Vincent Jousse, Frédéric Béchet, Yannick Estève, Georges Linares, et al.. La parole spontanée : transcription et traitement. Revue TAL, Association pour le Traitement Automatique des Langues, 2008. ⟨hal-01321127⟩
  • Christian Raymond, Frédéric Béchet, Nathalie Camelin, Renato de Mori, Géraldine Damnati. Sequential Decision Strategies for Machine Interpretation of Speech. IEEE Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2007, ⟨10.1109/TASL.2006.876862⟩. ⟨hal-01314620⟩
  • Christian Raymond, Frédéric Béchet, Renato de Mori, Géraldine Damnati. On the use of finite state transducers for semantic interpretation q. Speech Communication, Elsevier : North-Holland, 2006, ⟨10.1016/j.specom.2005.06.012⟩. ⟨hal-01314627⟩
  • Dilek Hakkani-Tü, Frédéric Béchet, Giuseppe Riccardi, Gokhan Tur. Beyond ASR 1-best: Using word confusion networks in spoken language understanding. Computer Speech and Language, Elsevier, 2005, ⟨10.1016/j.csl.2005.07.005⟩. ⟨hal-01314993⟩
  • Yannick Estève, Christian Raymond, Frédéric Béchet, Renato de Mori. On the use of linguistic consistency in automatic speech recognition. IEEE Transactions on Speech and Audio Processing, Institute of Electrical and Electronics Engineers (IEEE), 2003, 11 (6), pp.746--756. ⟨hal-01434539⟩
  • F. Yvon, P Boula de Mareüil, Christophe d'Alessandro, V Aubergé, M Bagein, et al.. Objective evaluation of grapheme to phoneme conversion for text-to-speech synthesis in French. Computer Speech and Language, Elsevier, 1998, 12, pp.393 - 410. ⟨hal-02000962⟩

Conference papers107 documents

  • Jeremy Auguste, Frédéric Béchet, Geraldine Damnati, Delphine Charlet. Skip Act Vectors: integrating dialogue context into sentence embeddings. Tenth International Workshop on Spoken Dialogue Systems Technology, Apr 2019, Syracuse, Italy. ⟨hal-02125259⟩
  • Frédéric Béchet, Christian Raymond. Benchmarking benchmarks: introducing new automatic indicators for benchmarking Spoken Language Understanding corpora. InterSpeech, Sep 2019, Graz, Austria. ⟨hal-02270633⟩
  • Gabriel Marzinotto, Geraldine Damnati, Frédéric Béchet. Adapting a FrameNet Semantic Parser for Spoken Language Understanding Using Adversarial Learning. Interspeech 2019, Sep 2019, Graz, Austria. pp.799-803, ⟨10.21437/Interspeech.2019-2732⟩. ⟨hal-02298417⟩
  • Gabriel Marzinotto, Geraldine Damnati, Frédéric Béchet, Benoit Favre. Robust Semantic Parsing with Adversarial Learning for Domain Generalization. Proceedings of the 2019 Conference of the North, Jun 2019, Minneapolis - Minnesota, France. pp.166-173, ⟨10.18653/v1/N19-2021⟩. ⟨hal-02298402⟩
  • Thibault Magallon, Frédéric Béchet, Benoit Favre. Détection d'erreurs dans des transcriptions OCR de documents historiques par réseaux de neurones récurrents multi-niveau. 25e conférence sur le Traitement Automatique des Langues Naturelles (TALN), May 2018, Rennes, France. ⟨hal-01905258⟩
  • Thibault Magallon, Frédéric Béchet, Benoit Favre. Fusion multimodale image/texte par réseaux de neurones profonds pour la classification de documents imprimés. 15e Conférence en Recherche d’Information et Applications (CORIA), May 2018, Rennes, France. ⟨hal-01905242⟩
  • Gabriel Marzinotto, Jeremy Auguste, Frederic Bechet, Géraldine Damnati, Alexis Nasr. Semantic Frame Parsing for Information Extraction : the CALOR corpus. LREC2018, May 2018, Miyazaki, Japan. ⟨hal-01959187⟩
  • Gabriel Marzinotto, Frédéric Béchet, Géraldine Damnati, Alexis Nasr. Sources of Complexity in Semantic Frame Parsing for Information Extraction. International FrameNet Workshop 2018, May 2018, Miyazaki, Japan. ⟨hal-01731385v2⟩
  • Jeremy Auguste, Delphine Charlet, Géraldine Damnati, Benoit Favre, Frédéric Bechet. Évaluation automatique de la satisfaction client à partir de conversations de type "chat" par réseaux de neurones récurrents avec mécanisme d’attention. 25e conférence sur le Traitement Automatique des Langues Naturelles (TALN), 2018, Rennes, France. ⟨hal-01943265⟩
  • Sebastien Delecraz, Leonor Becerra-Bonache, Benoit Favre, Alexis Nasr, Frédéric Béchet. Correction automatique d'attachements prépositionnels par utilisation de traits visuels. 25ème conférence sur le Traitement Automatique des Langues Naturelles, May 2018, Rennes, France. ⟨hal-01832979⟩
  • Sebastien Delecraz, Alexis Nasr, Frédéric Béchet, Benoit Favre. Adding Syntactic Annotations to Flickr30k Entities Corpus for Multimodal Ambiguous Prepositional-Phrase Attachment Resolution. 11th edition of the Language Resources and Evaluation Conference, May 2018, Miyazaki, Japan. ⟨hal-01832930⟩
  • Frédéric Béchet, Christian Raymond. Is ATIS too shallow to go deeper for benchmarking Spoken Language Understanding models?. InterSpeech 2018, Sep 2018, Hyderabad, India. pp.1-5. ⟨hal-01835425⟩
  • Géraldine Damnati, Jeremy Auguste, Alexis Nasr, Delphine Charlet, Johannes Heinecke, et al.. Handling Normalization Issues for Part-of-Speech Tagging of Online Conversational Text. Eleventh International Conference on Language Resources and Evaluation (LREC 2018), 2018, Miyazaki, Japan. ⟨hal-01943391⟩
  • Gabriel Marzinotto, Géraldine Damnati, Frederic Bechet. Analyse automatique FrameNet : une étude sur un corpus français de textes encyclopédiques. TALN 2017, 2017, Orléans, France. ⟨hal-01959260⟩
  • Frédéric Béchet, Géraldine Damnati, Johannes Heinecke, Gabriel Marzinotto, Alexis Nasr. CALOR-Frame : un corpus de textes encyclopédiques annoté en cadres sémantiques. ACor4French – Les corpus annotés du français - Atelier TALN, Jun 2017, Orléans, France. ⟨hal-01780348⟩
  • Benoit Favre, Frédéric Béchet, Géraldine Damnati, Delphine Charlet. Apprentissage d'agents conversationnels pour la gestion de relations clients. 24e Conférence sur le Traitement Automatique des Langues Naturelles (TALN), 2017, Orleans, France. ⟨hal-01773218⟩
  • Sebastien Delecraz, Alexis Nasr, Frédéric Béchet, Benoit Favre. Correcting prepositional phrase attachments using multimodal corpora. The 15th International Conference on Parsing Technologies, Sep 2017, Pise, Italy. ⟨hal-01693292⟩
  • Alexis Nasr, Geraldine Damnati, Aleksandra Guerraz, Frederic Bechet. Syntactic parsing of chat language in contact center conversation corpus. Annual SIGdial Meeting on Discourse and Dialogue, Sep 2016, Los Angeles, United States. pp.175 - 184, ⟨10.18653/v1/W16-3621⟩. ⟨hal-01454768⟩
  • Jérémy Trione, Benoit Favre, Frédéric Béchet. Beyond utterance extraction: summary recombination for speech summarization. Interspeech, San Francisco (USA), 2016, Unknown, Unknown Region. ⟨hal-01454927⟩
  • Sebastien Delecraz, Frédéric Béchet, Benoit Favre, Mickael Rouvier. Fusion d'espaces de représentations multimodaux pour la reconnaissance du rôle du locuteur dans des documents télévisuels. Actes de la conférence JEP 2016, 2016, Paris, France. ⟨hal-01454928⟩
  • Jérémy Trione, Benoit Favre, Frédéric Béchet. Détection de concepts pertinents pour le résumé automatique de conversations par recombinaison de patrons. Actes de la conférence TALN 2016, 2016, Paris, France. ⟨hal-01454926⟩
  • Carole Lailler, Anaïs Landeau, Frédéric Béchet, Yannick Estève, Paul Deléglise. Enhancing the RATP-DECODA corpus with linguistic annotations for performing a large range of NLP tasks. 10th edition of the Language Resources and Evaluation Conference (LREC 2016), 2016, Portorož, Slovenia. ⟨hal-01433189⟩
  • Jeremie Tafforeau, Frédéric Béchet, Thierry Artières, Benoit Favre. Joint syntactic and semantic analysis with a multitask Deep Learning Framework for Spoken Language Understanding. Interspeech, ISCA, 2016, San Francisco, United States. ⟨hal-01454929⟩
  • Frédéric Béchet, Benoit Favre, Mickael Rouvier. ``Speech is silver, but silence is golden'': improving speech-to-speech translation performance by slashing users input. Interspeech, 2015, Unknown, Unknown Region. ⟨hal-01194229⟩
  • Jeremy Trione, Frédéric Béchet, Benoit Favre, Alexis Nasr. Rapid FrameNet annotation of spoken conversation transcripts. Joint ACL-ISO Workshop on Interoperable Semantic Annotation, 2015, Unknown, Unknown Region. ⟨hal-01194232⟩
  • Benoit Favre, Evgeny Stepanov, Jérémy Trione, Frédéric Béchet, Giuseppe Riccardi. Call Centre Conversation Summarization: A Pilot Task at Multiling 2015. Sigdial, 2015, Unknown, Unknown Region. ⟨hal-01194231⟩
  • Frédéric Béchet, Meriem Bendris, Delphine Charlet, Géraldine Damnati, Benoit Favre, et al.. Identification de personnes dans des flux multimédia. CORIA 2015 - Conférence en Recherche d'Infomations et Applications - 12th French Information Retrieval Conference, Mar 2015, PARIS, France. pp.239-251. ⟨hal-01194234⟩
  • Mickael Rouvier, Sebastien Delecraz, Benoit Favre, Meriem Bendris, Frédéric Bechet. Multimodal embedding fusion for robust speaker role recognition in video broadcast. Automatic Speech Recognition and Understanding, Dec 2015, Scottsdale, United States. pp.383 - 389, ⟨10.1109/ASRU.2015.7404820⟩. ⟨hal-01475413⟩
  • Jeremie Tafforeau, Thierry Artières, Benoit Favre, Frédéric Béchet. Adapting lexical representation and OOV handling from written to spoken language with word embedding. Interspeech, 2015, Dresden, Germany. ⟨hal-01194228⟩
  • Frédéric Béchet, Meriem Bendris, Delphine Charlet, Géraldine Damnati, Benoit Favre, et al.. Multimodal understanding for person recognition in video broadcasts. Interspeech, Singapore, 2014, Unknown, Unknown Region. ⟨hal-01194244⟩
  • Mickael Rouvier, Benoit Favre, Frédéric Béchet. Correction interactive de transcriptions de parole par fusion de phrases. Actes de la conférence JEP 2014, 2014, Le Mans, France. ⟨hal-01194238⟩
  • Frédéric Béchet, Benoit Favre. Détection et caractérisation d’erreurs dans des transcriptions automatiques pour des systèmes de traduction parole-parole. Actes de la conférence JEP 2014, 2014, Le Mans, France. ⟨hal-01194239⟩
  • Frédéric Béchet, Benoit Favre, Alexis Nasr, Mathieu Morey. Retrieving the syntactic structure of erroneous ASR transcriptions for open-domain Spoken Language Understanding. ICASSP2014 - Speech and Language Processing (ICASSP2014 - SLTC), 2014, Florence, Italy. ⟨hal-01194236⟩
  • Benoit Favre, Mickael Rouvier, Frédéric Béchet. Reranked aligners for interactive transcript correction. ICASSP2014 - Speech and Language Processing (ICASSP2014 - SLTC), 2014, Florence, Italy. ⟨hal-01194237⟩
  • Frédéric Béchet, Alexis Nasr, Benoit Favre. Adapting dependency parsing to spontaneous speech for open domain spoken language understanding. Interspeech, Singapore, 2014, Unknown, Unknown Region. ⟨hal-01194246⟩
  • Michael Rouvier, Benoit Favre, Frédéric Béchet. Joint Decoding of Complementary Utterances. Spoken Languge Technologies (SLT), Lake Tahoe (USA), 2014, Unknown, Unknown Region. ⟨hal-01194247⟩
  • Alexis Nasr, Frédéric Béchet, Benoit Favre, Thierry Bazillon, José Deulofeu, et al.. Automatically enriching spoken corpora with syntactic information for linguistic studies. LREC, 2014, Unknown, Unknown Region. ⟨hal-01194241⟩
  • Frédéric Béchet, Benoit Favre. Asr Error Segment Localization for Spoken Recovery Strategy. IEEE International Conference in Acoustics, Speech and Signal Processing (ICASSP), Vancouver (Canada), 2013, Unknown, Unknown Region. ⟨hal-01194252⟩
  • Necip Fazil Ayan, Arindam Mandal, Michael Frandsen, Jing Zheng, Peter Blasco, et al.. Can You Give Me Another Word for Hyperbaric?: Improving Speech Translation using Targeted Clarification Questions. IEEE International Conference in Acoustics, Speech and Signal Processing (ICASSP), Vancouver (Canada), 2013, Unknown, Unknown Region. ⟨hal-01194251⟩
  • Favre Benoit, Géraldine Damnati, Frédéric Béchet, Meriem Bendris, Delphine Charlet, et al.. PERCOLI: a person identification system for the 2013 REPERE challenge. SLAM 2013 : First Workshop on Speech, Language and Audio in Multimedia, Aug 2013, Marseille, France. pp.55-60. ⟨hal-00834204⟩
  • Frédéric Béchet, Rémi Auguste, Stéphane Ayache, Delphine Charlet, Géraldine Damnati, et al.. Percol0 - un système multimodal de détection de personnes dans des documents vidéo (Percol0 - A multimodal person detection system in video documents) [in French]. Actes de la conférence conjointe JEP-TALN-RECITAL 2012, volume 1: JEP, 2012, Grenoble, France. pp.553--560. ⟨hal-01194254⟩
  • Frederic Bechet, Benoit Favre, Géraldine Damnati. Detecting Person Presence in TV Shows with Linguistic and Structural Features. IEEE International Conference in Acoustics, Speech and Signal Processing (ICASSP), Kyoto (Japan), 2012, Unknown, Unknown Region. ⟨hal-01194256⟩
  • Thierry Bazillon, Melanie Delplano, Frédéric Béchet, Alexis Nasr, Benoit Favre. Syntactic annotation of spontaneous speech: application to call-center conversation data. LREC'12, Istambul, Turkey, 2012, Unknown, Unknown Region. ⟨hal-01194255⟩
  • Rosa Stern, Benoît Sagot, Frédéric Béchet. A Joint Named Entity Recognition and Entity Linking System. EACL 2012 Workshop on Innovative hybrid approaches to the processing of textual data, Apr 2012, Avignon, France. ⟨hal-00699295⟩
  • Alexis Nasr, Frédéric Béchet, Jean-François Rey, Benoit Favre, Joseph Le Roux. MACAON : An NLP Tool Suite for Processing Word Lattices. ACL 2011, 2011, United States. pp.86-91. ⟨hal-00702442⟩
  • Liva Ralaivola, Benoit Favre, Pierre Gotab, Frédéric Béchet, Géraldine Damnati. Applying Multiclass Bandit algorithms to call-type classification. IEEE Automatic Speech Recognition and Understanding Workshop (ASRU'11), 2011, Unknown, Unknown Region. ⟨hal-01194262⟩
  • Alexis Nasr, Frédéric Béchet, Jean-François Rey, Benoit Favre, Joseph Le Roux. MACAON: an NLP tool suite for processing word lattices. Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: Systems Demonstrations, 2011, Unknown, Unknown Region. pp.86--91. ⟨hal-01194259⟩
  • Frédéric Béchet, Benoît Sagot, Rosa Stern. Coopération de méthodes statistiques et symboliques pour l'adaptation non-supervisée d'un système d'étiquetage en entités nommées. TALN'2011 - Traitement Automatique des Langues Naturelles, Jun 2011, Montpellier, France. ⟨inria-00617068⟩
  • Alexis Nasr, Frédéric Béchet, Jean-François Rey, Benoit Favre, Joseph Le Roux. MACAON:A linguistic tool suite for processing word lattices. The 49th Annual Meeting of the Association for Computational Linguistics: demonstration session, 2011, Unknown, Unknown Region. ⟨hal-01194861⟩
  • Thierry Bazillon, Benjamin Maza, Michael Rouvier, Frédéric Béchet, Alexis Nasr. Qui êtes vous ? Catégoriser les questions pour déterminer le rôle des locuteurs dans des conversations orales. Traitement Automatique des Langues Naturelles, 2011, Unknown, Unknown Region. ⟨hal-01196021⟩
  • Thierry Bazillon, Benjamin Maza, Michael Rouvier, Frédéric Béchet, Alexis Nasr. Speaker Role Recognition using question detection and characterization. Interspeech, 2011, Unknown, Unknown Region. ⟨hal-01196022⟩
  • Yannick Estève, Thierry Bazillon, Jean-Yves Antoine, Frédéric Béchet, Jérôme Farinas. The EPAC corpus: manual and automatic annotations of conversational speech in French broadcast news. LREC 2010, 2010, Unknown, Malta. ⟨hal-01433895⟩
  • Richard Dufour, Yannick Estève, Paul Deléglise, Frédéric Béchet. Utilisation conjointe de modèles locaux et globaux pour la caractérisation et la détection de segments de parole spontanée. JEP 2010, 2010, Mons, Belgium. ⟨hal-01433896⟩
  • Christophe Servan, Nathalie Camelin, Christian Raymond, Frédéric Béchet, Renato de Mori. On the Use of Machine Translation for Spoken Language Understanding Portability. IEEE International Conference on Acoustics, Speech, and Signal Processing, IEEE, Mar 2010, Dallas, Texas, United States. pp.5330 - 5333, ⟨10.1109/ICASSP.2010.5494960⟩. ⟨inria-00523967⟩
  • Frédéric Béchet, Christian Raymond, Frédéric Duvert, Renato de Mori. Frame based interpretation of conversational speech. Spoken Language Technology Workshop (SLT), 2010, IEEE, Dec 2010, Berkeley, CA, United States. ⟨10.1109/SLT.2010.5700886⟩. ⟨inria-00561131⟩
  • Frederic Bechet, Eric Charton. Unsupervised knowledge acquisition for Extracting Named Entities from speech. IEEE International Conference on Acoustics, Speech and Signal Processing , Mar 2010, Dallas, United States. ⟨10.1109/ICASSP.2010.5494962⟩. ⟨hal-01312857⟩
  • Alexis Nasr, Frédéric Béchet, Jean-François Rey. MACAON : Une chaîne linguistique pour le traitement de graphes de mots. Traitement Automatique des Langues Naturelles, 2010, Montréal, Unknown Region. ⟨hal-01196023⟩
  • Richard Dufour, Yannick Estève, Paul Deléglise, Frédéric Béchet. Local and global models for spontaneous speech segment detection and characterization. IEEE ASRU 2009, 2009, Merano, Italy. ⟨hal-01433914⟩
  • Juan-Manuel Torres-Moreno, Marc El Bèze, Frédéric Béchet, Nathalie Camelin. Fusion probabiliste appliquée à la détection et classification d'opinions. Défi Fouille de Texte (DEFT'09), 2009, Paris, Unknown Region. ⟨hal-01433913⟩
  • Richard Dufour, Vincent Jousse, Yannick Estève, Frédéric Béchet, Georges Linarès. Spontaneous Speech Characterization and Detection in Large Audio Database. 13-th International Conference on Speech and Computer (SPECOM 2009), 2009, St Petersburg, Russia. ⟨hal-01433943⟩
  • Nathalie Camelin, Renato de Mori, Frederic Bechet, Geraldine Damnati. Error correction of proportions in spoken opinion surveys. Interspeech, Sep 2009, Brighton, United Kingdom. ⟨hal-01314530⟩
  • Pierre Gotab, Frederic Bechet #2, Geraldine Damnati. Active learning for rule-based and corpus-based Spoken Language Understanding models. IEEE Workshop on Automatic Speech Recognition & Understanding, 2009. ASRU 2009, Dec 2009, Merano, Italy. ⟨10.1109/ASRU.2009.5373377⟩. ⟨hal-01317421⟩
  • Nathalie Camelin, Frédéric Béchet, Renato de Mori, Géraldine Damnati. Analyse des erreurs d'une stratégie automatique de sondages téléphonique d'opinion. Journées d'Étude sur la Parole (JEP'08), 2008, Avignon, Unknown Region. ⟨hal-01434052⟩
  • Nathalie Camelin, Géraldine Damnati, Frédéric Béchet, Renato de Mori. Automatic customer feedback processing : alarm detection in open question spoken messages. Interspeech 2008, 2008, Brisbane, Australia. ⟨hal-01434050⟩
  • Christophe Servan, Frederic Bechet. Fast call-classification system development without in-domain training data. The proceedings of the International Conference on Speech and Language Processing (ICSLP) Interspeech 2008, Sep 2008, Brisbane, Australia. ⟨hal-01158650⟩
  • Marie-Jean Meurs, Frédéric Duvert, Frédéric Béchet, Fabrice Lef, Renato de Mori. Semantic Frame Annotation on the French MEDIA corpus. Language Resources and Evaluation Conference, 2008, Marrakech, France. ⟨hal-01311400⟩
  • Vincent Jousse, Yannick Estève, Frédéric Béchet, Thierry Bazillon, Georges Linares. Caractérisation et détection de parole spontanée dans de larges collections de documents audio. JEP, Jun 2008, Avignon, France. ⟨hal-01317613⟩
  • Stanislas Oger, Georges Linarès, Frédéric Béchet, Pascal Nocera. Enrichissement dynamique du vocabulairè a partir du Web. JEP, Jun 2008, Avignon, France. ⟨hal-01319845⟩
  • Vincent Jousse, Yannick Estève, Frédéric Béchet, Thierry Bazillon, Georges Linares. Caractérisation et détection de parole spontanée dans de larges collections de documents audio. JEP, Jun 2008, Avignon, France. ⟨hal-01321187⟩
  • Stanislas Oger, Georges Linarès, Frédéric Béchet. Local methods for on-demand out-of-vocabulary word retrieval. LREC, May 2008, Marrakech, Morocco. ⟨hal-01319850⟩
  • Stanislas Oger, Georges Linarès, Frédéric Béchet, Pascal Nocera. On-demand new word learning using world wide web. IEEE International Conference on Acoustics, Speech and Signal Processing , Mar 2008, Las Vegas, United States. ⟨10.1109/ICASSP.2008.4518607⟩. ⟨hal-01319857⟩
  • Nathalie Camelin, Geraldine Damnati, Frederic Bechet, Renato de Mori. Automatic customer feedback processing: alarm detection in open question spoken messages. Interspeech, Sep 2008, brisbane, Australia. ⟨hal-01314565⟩
  • Frédéric Duvert, Marie-Jean Meurs, Christophe Servan, Frédéric Béchet, Fabrice Lefèvre, et al.. Semantic composition process in a speech understanding system. The 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Mar 2008, Las Vegas, United States. ⟨10.1109/ICASSP.2008.4518788⟩. ⟨hal-01158578⟩
  • Frédéric Duvert, Marie-Jean Meurs, Christophe Servan, Frédéric Béchet, Fabrice Lefèvre, et al.. Composition sémantique pour la compréhension de la parole dans un cadre de dialogue. Les 27e Journées d’Etudes sur la Parole (JEP), Jun 2008, Avignon, France. ⟨hal-01159983⟩
  • Frédéric Duvert, Marie-Jean Meurs, Christophe Servan, Frédéric Béchet, Fabrice Lefèvre, et al.. Composition sémantique pour la compréhension de la parole dans le cadre de dialogue. Journées d'Etude sur la Parole (JEP), 2008, Avignon, France. ⟨hal-01434056⟩
  • Juan-Manuel Torres-Moreno, Marc El Bèze, Frédéric Béchet, Nathalie Camelin. Comment faire pour que l'opinion forgée à la sortie des urnes soit la bonne? Application au défi DEFT'07. Défi Fouille de Texte (DEFT'07), 2007, Grenoble, Unknown Region. ⟨hal-01434071⟩
  • Géraldine Damnati, Frédéric Béchet, Renato de Mori. Experiments on the France Telecom 3000 Voice Agency corpus: academic research on an industrial spoken dialog system. NAACL-HLT-Dialog '07, Apr 2007, Rochester, United States. ⟨hal-01317176⟩
  • Géraldine Damnati, Frédéric Béchet, Renato de Mori. SPOKEN LANGUAGE UNDERSTANDING STRATEGIES ON THE FRANCE TELECOM 3000 VOICE AGENCY CORPUS Ge'raldine Damnati1, Fre'deric Bechet2. IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07 , Apr 2007, Honolulu, United States. ⟨hal-01317193⟩
  • Alexandre Denis, Frédéric Béchet, Matthieu Quignard. Résolution de la référence dans des dialogues homme-machine : évaluation sur corpus de deux approches symbolique et probabiliste. Actes de la 14e conférence sur le Traitement Automatique des Langues Naturelles - TALN 2007, Jun 2007, Toulouse, France. pp.261-270. ⟨inria-00179697⟩
  • Nathalie Camelin, Frédéric Béchet, Géraldine Damnati, Renato de Mori. Analyse automatique de sondages téléphoniques d'opinion. TALN récital, Jun 2007, Toulouse, France. ⟨hal-01314513⟩
  • Juan-Manuel Torres-Moreno, Marc El Bèze, Frédéric Béchet, Nathalie Camelin. Comment faire pour que l opinion forgée à la sortie des urnes soit la bonne ? Application au défi DEFT 2007. DEFT2007 troisième DÉfi Fouille de Textes, Jul 2007, Grenoble, France. ⟨hal-01321139⟩
  • Abdillahi Nimaan, Pascal Nocera, Frédéric Bechet, Jean-François Bonastre. Information Retrieval Strategies for Accessing African Audio Corpora. INTERSPEECH, Aug 2007, Anvers, Belgium. ⟨hal-01319828⟩
  • Nathalie Camelin, Frédéric Béchet, Géraldine Damnati, Renato de Mori. Speech Mining in Noisy Audio Message Corpus. Interspeech, Aug 2007, Anvers, Belgium. ⟨hal-01314518⟩
  • Bogdan Minescu, Géraldine Damnati, Fréderic Béchet, Renato de Mori. Conditional use of Word Lattices, Confusion Networks and 1-best string hypotheses in a Sequential Interpretation Strategy. Interspeech, Aug 2007, Anvers, Belgium. ⟨hal-01312935⟩
  • Christophe Servan, Christian Raymond, Frédéric Béchet, Pascal Nocera. Décodage conceptuel à partir de graphes de mots sur le corpus de dialogue Homme-Machine MEDIA. Les XXVIes Journées d'Étude sur la Parole (JEP 2006), Jun 2006, Dinard, France. ⟨hal-01160185⟩
  • Frédéric Béchet, Géraldine Damnati, Nathalie Camelin, Renato de Mori. Spoken opinion extraction for detecting variations in user satisfaction. IEEE/ACL Workshop on Spoken Language Technology (SLT'06), 2006, Unknown, Aruba. ⟨hal-01434200⟩
  • Christophe Servan, Frédéric Béchet. Décodage conceptuel et apprentissage automatique : application au corpus de dialogue Homme-Machine MEDIA. La 13ème édition de la conférence sur le Traitement Automatique des Langues Naturelles (TALN 2006), Apr 2006, Louvain, Belgium. ⟨hal-01160173⟩
  • Christophe Servan, Christian Raymond, Frédéric Béchet, Pascal Nocera. Conceptual decoding from word lattices: application to the spoken dialogue corpus MEDIA. The Ninth International Conference on Spoken Language Processing (Interspeech 2006 - ICSLP), Sep 2006, Pittsburgh, United States. ⟨hal-01160181⟩
  • Nathalie Camelin, Géraldine Damnati, Frédéric Béchet, Renato de Mori. Détection automatique d’opinions dans des corpus de messages oraux. Les Journées d’Etude sur la Parole (JEP), Jun 2006, Dinard, France. ⟨hal-01314570⟩
  • Nathalie Camelin, Géraldine Damnati, Frédéric Béchet, Renato de Mori. Opinion mining in a telephone survey corpus. Interspeech, Sep 2006, Pittsburgh, United States. ⟨hal-01314579⟩
  • Benoit Favre, Frédéric Béchet, Patrice Bellot, Florian Boudin, Marc El Bèze, et al.. The LIA-Thales summarization system at DUC-2006. Document Understanding Conference Workshop, HLT-NAACL'06, New York (USA), 2006, Unknown, Unknown Region. ⟨hal-01194297⟩
  • H Bonneau-Maynard, C Ayache, F Bechet, Alexandre Denis, A Kuhn, et al.. Results of the French Evalda-Media evaluation campaign for literal understanding. The fifth international conference on Language Resources and Evaluation (LREC 2006), May 2006, Genes, Italy. ⟨hal-01160167⟩
  • Christian Raymond, Frédéric Béchet, Nathalie Camelin, Renato de Mori, Géraldine Damnati. Semantic interpretation with error correction. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'05), 2005, Philadelphia (USA), Unknown Region. ⟨hal-01434257⟩
  • Philippe Boula de Mareüil, Christophe d'Alessandro, Gérard Bailly, Frédéric Béchet, Marie-Neige Garcia, et al.. Evaluating the pronunciation of proper names by four French grapheme-to-phoneme converters. 2005, pp.1521-1524. ⟨hal-00103607⟩
  • Benoit Favre, Frédéric Béchet, Pascal Nocera. Mining Broadcast News data: Robust Information Extraction from Word Lattices. Proceeding of Eurospeech'05, Lisboa (Portugal), 2005, Unknown, Unknown Region. ⟨hal-01194300⟩
  • Benoit Favre, Frédéric Béchet, Pascal Nocera. Robust Named Entity Extraction from Spoken Archives. Proceedings of HLT-EMNLP'05, Vancouver (Canada), 2005, Unknown, Unknown Region. ⟨hal-01194299⟩
  • Georges Linares, Pascal Nocera, Driss Matrouf, F Béchet, D Massonié, et al.. Le système de transcription du LIA pour ESTER-2005. ESTER 2005, Mar 2005, Avignon, France. ⟨hal-01318289⟩
  • Christian Raymond, Frédéric Béchet, Renato de Mori, Géraldine Damnati, Yannick Estève. Automatic learning of interpretatation strategies for spoken dialogue systems. ICASSP 2004, 2004, Montréal, Canada. ⟨hal-01434523⟩
  • Hélène Maynard, Kevin Mctait, Djamel Mostefa, Laurence Devillers, Sophie Rosset, et al.. Constitution d'un corpus de dialogue oral pour l'évaluation automatique de la compréhension hors- et en- contexte du dialogue. Journées d'Etudes sur la Parole - JEP 2004, 2004, Fès, Maroc. pp.357-360. ⟨inria-00100201⟩
  • Yannick Estève, Christian Raymond, Frédéric Béchet, Renato de Mori. Conceptual decoding for spoken dialog systems. Eurospeech 2003, 2003, Genêve, Switzerland. pp.3033--3336. ⟨hal-01434559⟩
  • Christian Raymond, Yannick Estève, Frédéric Béchet, Renato de Mori, Géraldine Damnati. Belief confirmation in spoken dialog systems using confidence measures. ASRU 2003, 2003, St Thomas, US Virgin Islands (USA), Unknown Region. ⟨hal-01434556⟩
  • Yannick Estève, Frédéric Béchet, A. Nasr, Renato de Mori. Stochastic finite state automata triggered by dialogue states. Eurospeech 2001, 2001, Aalborg, Denmark. pp.725--728. ⟨hal-01434645⟩
  • Frédéric Béchet, Yannick Estève, Renato de Mori. Modèles de langage hiérarchiques pour les applications de dialogue en parole spontanée. TALN 2001, 2001, Tours, France. pp.327--332. ⟨hal-01434626⟩
  • Frédéric Béchet, Yannick Estève, Renato de Mori. Tree-based language model dedicated to natural spoken dialogs systems. ISCA TRW on Adaptation methods for speech recognition, 2001, Sophia-Antipolis, France. ⟨hal-01434642⟩
  • Yannick Estève, Frédéric Béchet, Renato de Mori. Sélection dynamique de modèles de langage dans une application de dialogue. JEP 2000, 2000, Aussois, France. pp.185--188. ⟨hal-01434683⟩
  • Yannick Estève, Frédéric Béchet, Renato de Mori. Dynamic selection of language models in a dialog system. ICSLP 2000, 2000, Pékin Beijing, China. pp.214--217. ⟨hal-01434686⟩
  • Alexis Nasr, Yannick Estève, Frédéric Béchet, Thierry Spriet, Renato de Mori. A language model combining n-grams and stochastic finite state automata. Eurospeech 1999, 1999, Budapest, Hungary. pp.2175--2178. ⟨hal-01434731⟩

Poster communications1 document

  • Jeremy Auguste, Delphine Charlet, Geraldine Damnati, Frédéric Béchet, Benoit Favre. Can we predict self-reported customer satisfaction from interactions ?. International Conference on Acoustics, Speech and Signal Processing, May 2019, Brighton, United Kingdom. ⟨hal-02134252⟩

Book sections3 documents

  • Juan-Manuel Torres-Moreno, Marc El-Bèze, Patrice Bellot, Frédéric Béchet. Opinion Detection as a Topic Classification Problem. F. Yvon et E. Gaussier. Textual Information Access: Statistical Models, 9, 2012. ⟨hal-01488020⟩
  • Christophe d'Alessandro, Philippe Boula de Mareüil, Marie-Neige Garcia, Gérard Bailly, Michel Morel, et al.. La campagne EvaSy d'évaluation de la synthèse de la parole à partir du texte. S. Chaudiron et K. Choukri. L'évaluation des technologies de traitement de la langue, Hermès, pp.183-208, 2008, Cognition et traitement de l'information. ⟨hal-00361911⟩
  • Hélène Bonneau-Maynard, Alexandre Denis, Frédéric Béchet, Laurence Devillers, Fabrice Lefèvre, et al.. Media : évaluation de la compréhension dans les systèmes de dialogue. Stéphane Chaudiron; Khalid Choukri. L'évaluation des technologies de traitement de la langue, les campagnes Technolangue, Hermès, Lavoisier, pp.209-232, 2008, Cognition et traitement de l'information, 978-2746219922. ⟨hal-00337343⟩

Directions of work or proceedings1 document

  • Guillaume Gravier, Frédéric Béchet. Proceedings of the First ISCA/IEEE Workshop on Speech, Language and Audio in Multimedia. Guillaume Gravier and Frédéric Béchet. First ISCA/IEEE Workshop on Speech, Language and Audio in Multimedia, Aug 2013, France. 2012, 2013. ⟨hal-01038124⟩