Yannick Estève
Professor in Computer Science - Head of LIA - Avignon University
36
Documents
Identifiants chercheurs
- yannick-esteve
- 0000-0002-3656-8883
- Google Scholar : https://scholar.google.fr/citations?user=dQDAeBYAAAAJ&hl=fr&oi=ao
- IdRef : 070531668
Présentation
My main research interests are speech and language processing.
I have studied Computer Science (Licence and Master's degree) at the Faculty of Sciences of Luminy (Marseille, France). I obtained my PhD on 2002, under the direction of Pr. Renato De Mori, at the Computer Science Labs (LIA) of the University of Avignon (Avignon, France), in association with France Telecom R&D (FTRD, now Orange Labs).
I have worked since June 2002 with FTRD as a research engineer, then as a post-doctoral researcher until August 2003.
Then, I have worked until 2018 at the Computer Science Labs (LIUM) of the University of Le Mans (France), from September 2003 as an associate professor, becoming a full professor in 2010.
I have headed the [LIUM](https://lium.univ-lemans.fr/en/) from 2012 to 2016 and was a co-founder of the Language and Speech Technology (LST) team of this lab.
From 2015 to 2018, I was also the head of the Claude Chappe Informatics Institute that coordinates research, teaching, and innovation activities on computer science at the University of Le Mans.
In 2018, I moved to the Computer Science Labs of Avignon (LIA) at the University of Avignon.
In May 2020, I became the head of [LIA](https://lia.univ-avignon.fr/en/).
My current research activities focus on spoken language understanding, speech translation, speech analytics, speech recognition, deep neural networks, word embeddings, hidden representation.
Currently , I am leading the E-SSL project funded by the ANR (French Research Agency) on efficient self supervised learning for speech processing, and I am the LIA scientific responsible in the H2020 SELMA project focusing on transfer learning and user feedback for speech and language processing.
Domaines de recherche
Publications
- 4
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 36
- 15
- 5
- 5
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 28
- 6
- 1
- 3
- 1
- 2
- 3
- 7
- 4
- 7
- 6
- 1
- 2
- 1
- 3
- 2
- 1
- 1
- 1
- 2
|
A study of continuous space word and sentence representations applied to ASR error detectionSpeech Communication, 2020
Article dans une revue
hal-02501943v1
|
|
Impact Analysis of the Use of Speech and Language Models Pretrained by Self-Supersivion for Spoken Language UnderstandingLREC 2022, Jun 2022, Marseille, France
Communication dans un congrès
hal-03706925v1
|
|
The Spoken Language Understanding MEDIA Benchmark Dataset in the Era of Deep Learning: data updates, training and evaluation toolsLREC 2022, Jun 2022, Marseille, France
Communication dans un congrès
hal-03706938v1
|
|
Le benchmark MEDIA revisité : données, outils et évaluation dans un contexte d'apprentissage profondXXXIVe Journées d'Études sur la Parole -- JEP 2022, Jun 2022, île de Noirmoutier, France
Communication dans un congrès
hal-03770588v1
|
End2End Acoustic to Semantic TransductionICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Jun 2021, Toronto, ON, Canada. ⟨10.1109/ICASSP39728.2021.9413581⟩
Communication dans un congrès
hal-03128163v1
|
|
|
A Multimodal Educational Corpus of Oral Courses: Annotation, Analysis and Case StudyLREC, May 2020, Marseille, France
Communication dans un congrès
hal-02496700v1
|
|
Curriculum-based transfer learning for an effective end-to-end spoken language understanding and domain portability20th Annual Conference of the International Speech Communication Association (InterSpeech), Sep 2019, Graz, Austria. pp.1198-1202, ⟨10.21437/interspeech.2019-1832⟩
Communication dans un congrès
hal-02304597v1
|
An Empirical Evaluation of Arabic-Specific Embeddings for Sentiment AnalysisInternational Conference on Arabic Language Processing, Oct 2019, Nancy, France. pp.34-48, ⟨10.1007/978-3-030-32959-4_3⟩
Communication dans un congrès
hal-02320120v1
|
|
Plongements lexicaux spécifiques à la langue arabe : application à l'analyse d'opinions26e conférence sur le Traitement Automatique des Langues Naturelles (TALN 2019), Jul 2019, Toulouse, France. pp.381-390
Communication dans un congrès
hal-02567780v1
|
|
Représentations de phrases dans un espace continu spécifiques à la tâche de détection d'erreursXXXIIe Journées d'Etudes sur la Parole (JEP 2018), Jun 2018, Aix-en-Provence, France
Communication dans un congrès
hal-01757774v1
|
|
|
Simulation d'erreurs de reconnaissance automatique dans un cadre de compréhension de la paroleXXXIIe Journées d'Etudes sur la Parole (JEP 2018), Jun 2018, Aix-en-Provence, France
Communication dans un congrès
hal-01757770v1
|
|
Des représentations continues de mots pour l'analyse d'opinions en arabe: une étude qualitative25e conférence sur le Traitement Automatique des Langues Naturelles (TALN 2018), May 2018, Rennes, France
Communication dans un congrès
hal-01757776v2
|
FrNewsLink : a corpus linking TV Broadcast News Segments and Press ArticlesLREC - Language Resources Evaluation Conference, May 2018, Miyazaki, Japan
Communication dans un congrès
hal-01741177v1
|
|
Task Specific Sentence Embeddings for ASR Error DetectionInterspeech 2018, Sep 2018, Hyderabad, India. ⟨10.21437/Interspeech.2018-2211⟩
Communication dans un congrès
hal-01870864v1
|
|
|
Simulating ASR errors for training SLU systemsLREC 2018, May 2018, Miyazaki, Japan
Communication dans un congrès
hal-01715923v1
|
|
Arabic Sentiment analysis: an empirical study of machine translation's impactLANGUAGE PROCESSING AND KNOWLEDGE MANAGEMENT INTERNATIONAL CONFERENCE (LPKM2018), Oct 2018, Sfax, Tunisia
Communication dans un congrès
hal-02042313v1
|
|
ASR error management for improving spoken language understandingInterspeech 2017, Aug 2017, Stockholm, Sweden
Communication dans un congrès
hal-01526298v1
|
|
Enriching confusion networks for post-processingStatistical Language and Speech Processing 2017, Oct 2017, Le Mans, France
Communication dans un congrès
hal-01585768v1
|
|
Evaluating Automatic Topic Segmentation as a Segment Retrieval TaskInterspeech 2017, Aug 2017, Stockholm, Sweden. pp.2924 - 2928, ⟨10.21437/Interspeech.2017-1231⟩
Communication dans un congrès
hal-01585769v1
|
Title assignment for automatic topic segments in TV Broadcast News41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), 2016, Shangai, China
Communication dans un congrès
hal-01433186v1
|
|
Word embedding evaluation and combination10th edition of the Language Resources and Evaluation Conference (LREC 2016), 2016, Portorož, Slovenia
Communication dans un congrès
hal-01433185v1
|
|
|
Des Réseaux de Neurones avec Mécanisme d’Attention pour la Compréhension de la Parole31ème Journées d’Études sur la Parole, 2016, Paris, France
Communication dans un congrès
hal-01433191v1
|
Recent improvements on error detection for automatic speech recognition1st International Workshop on Multimodal Media Data Analytics (MMDA 2016), in Conjunction with the 22nd European Conference on Artificial Intelligence, 2016, The Hague The, Netherlands
Communication dans un congrès
hal-01433168v1
|
|
Evaluation of acoustic word embeddingsRepEval@ACL 2016: The 1st Workshop on Evaluating Vector-Space Representations for NLP, 2016, Berlin, Germany
Communication dans un congrès
hal-01433181v1
|
|
Acoustic word embeddings for ASR error detectionInterspeech 2016, 2016, San Francisco (CA, USA), Unknown Region
Communication dans un congrès
hal-01433176v1
|
|
Utilisation des représentations continues des mots et des paramètres prosodiques pour la détection d’erreurs dans les transcriptions automatiques de la parole31ème Journées d’Études sur la Parole, 2016, Paris, France
Communication dans un congrès
hal-01450277v1
|
|
Which ASR errors are hard to detect?Workshop Errors by Humans and Machines in multimedia, multimodal and multilingual data processing (ERRARE 2015), 2015, Sinaia, Romania
Communication dans un congrès
hal-01433201v1
|
|
Word embeddings combination and neural networks for robustness in ASR error detection2015 European Signal Processing Conference (EUSIPCO 2015), 2015, Nice, France
Communication dans un congrès
hal-01433210v1
|
|
Combining continous word representation and prosodic features for ASR error prediction3rd International Conference on Statistical Language and Speech Processing (SLSP 2015), 2015, Budapest, Hungary
Communication dans un congrès
hal-01433203v1
|
|
Diachronic Semantic Cohesion for Topic Segmentation of TV Broadcast NewsInterspeech 2015, 2015, Dresden, Germany
Communication dans un congrès
hal-01450370v1
|
|
Segmentation et titrage automatique de journaux télévisésConférence sur le Traitement Automatique des Langues Naturelles (TALN), 2015, Caen, France
Communication dans un congrès
hal-01433208v1
|
|
|
Exploring the use of Attention-Based Recurrent Neural Networks For Spoken Language UnderstandingMachine Learning for Spoken Language Understanding and Interaction NIPS 2015 workshop (SLUNIPS 2015), 2015, Montreal, Canada
Communication dans un congrès
hal-01433202v1
|
An investigation of single-pass ASR system combination for Spoken Language Understanding1st International Conference on Statistical Language and Speech Processing (SLSP 2013), 2013, Tarragona, Spain
Communication dans un congrès
hal-01433263v1
|
|
Robustesse et portabilités multilingue et multi-domaines des systèmes de compréhension de la parole : les corpus du projet PortMediaActes de la conférence conjointe JEP-TALN-RECITAL 2012, volume 1: JEP, 2012, Grenoble, France. pp.779--786
Communication dans un congrès
hal-01194257v1
|
|
|
Leveraging study of robustness and portability of spoken language understanding systems across languages and domains: the PORTMEDIA corporaThe International Conference on Language Resources and Evaluation, May 2012, Istanbul, Turkey
Communication dans un congrès
hal-00683433v1
|