Paul Deléglise

Publication Activity (10 Years)

Years Active: 1982-2020
Publications (10 Years): 12

Top Topics

Person Identification

Automatic Speech Recognition

Language Understanding

Top Venues

JEP-TALN-RECITAL (1)

IWSLT (Evaluation Campaign)

Publications

Paul Deléglise, Carole Lailler
Quel type de systèmes utiliser pour la transcription automatique du français ? Les HMM font de la résistance (What system for the automatic transcription of French in audiovisual broadcasts ?). JEP-TALN-RECITAL (1) (2020)
Laurence Devillers, Sophie Rosset, Guillaume Dubuisson Duplessis, Lucile Bechade, Yucel Yemez, Bekir Berker Türker, T. Metin Sezgin, Engin Erzin, Kevin El Haddad, Stéphane Dupont, Paul Deléglise, Yannick Estève, Carole Lailler, Emer Gilmartin, Nick Campbell
Multifaceted Engagement in Social Interaction with a Machine: The JOKER Project. FG (2018)
Olivier Galibert, Nathalie Camelin, Paul Deléglise, Sophie Rosset
Estimation de la qualité d'un système de reconnaissance de la parole pour une tâche de compréhension (Quality estimation of a Speech Recognition System for a Spoken Language Understanding task). JEP-TALN-RECITAL (1) (2016)
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. LREC (2016)
Sahar Ghannay, Yannick Estève, Nathalie Camelin, Paul Deléglise
Evaluation of acoustic word embeddings. RepEval@ACL (2016)
Gaël Le Lan, Sylvain Meignier, Delphine Charlet, Paul Deléglise
Speaker diarization with unsupervised training framework. ICASSP (2016)
Sahar Ghannay, Yannick Estève, Nathalie Camelin, Paul Deléglise
Acoustic Word Embeddings for ASR Error Detection. INTERSPEECH (2016)
Paul Gay, Sylvain Meignier, Paul Deléglise, Jean-Marc Odobez
CRF-Based Context Modeling for Person Identification in Broadcast Videos. Frontiers ICT 3 (2016)
Edwin Simonnet, Paul Deléglise, Nathalie Camelin, Yannick Estève
Des Réseaux de Neurones avec Mécanisme d'Attention pour la Compréhension de la Parole (Exploring the use of Attention-Based Recurrent Neural Networks For Spoken Language Understanding ). JEP-TALN-RECITAL (1) (2016)
Vishwa Gupta, Paul Deléglise, Gilles Boulianne, Yannick Estève, Sylvain Meignier, Anthony Rousseau
CRIM and LIUM approaches for multi-genre broadcast media transcription. ASRU (2015)
Guillaume Dubuisson Duplessis, Lucile Bechade, Mohamed A. Sehili, Agnès Delaborde, Vincent Letard, Anne-Laure Ligozat, Paul Deléglise, Yannick Estève, Sophie Rosset, Laurence Devillers
Nao is doing humour in the CHIST-ERA joker project. INTERSPEECH (2015)
Mercedes García-Martínez, Loïc Barrault, Anthony Rousseau, Paul Deléglise, Yannick Estève
The LIUM ASR and SLT systems for IWSLT 2015. IWSLT (Evaluation Campaign) (2015)
Anthony Rousseau, Loïc Barrault, Paul Deléglise, Yannick Estève, Holger Schwenk, Samir Bennacef, Armando Muscariello, Stephan Vanni
LIUM English-to-French spoken language translation system and the Vecsys/LIUM automatic speech recognition system for Italian language for IWSLT 2014. IWSLT (Evaluation Campaign) (2014)
Anthony Rousseau, Gilles Boulianne, Paul Deléglise, Yannick Estève, Vishwa Gupta, Sylvain Meignier
LIUM and CRIM ASR System Combination for the REPERE Evaluation Campaign. TSD (2014)
Grégor Dupuy, Sylvain Meignier, Paul Deléglise, Yannick Estève
Recent Improvements on ILP-based Clustering for Broadcast News Speaker Diarization. Odyssey (2014)
Paul Gay, Elie Khoury, Sylvain Meignier, Jean-Marc Odobez, Paul Deléglise
A conditional random field approach for face identification in broadcast news using overlaid text. ICIP (2014)
Antoine Laurent, Sylvain Meignier, Paul Deléglise
Improving recognition of proper nouns in ASR through generating and filtering phonetic transcriptions. Comput. Speech Lang. 28 (4) (2014)
Anthony Rousseau, Paul Deléglise, Yannick Estève
Enhancing the TED-LIUM Corpus with Selected Data for Language Modeling and More TED Talks. LREC (2014)
Paul Gay, Grégor Dupuy, Carole Lailler, Jean-Marc Odobez, Sylvain Meignier, Paul Deléglise
Comparison of two methods for unsupervised person identification in TV shows. CBMI (2014)
Richard Dufour, Yannick Estève, Paul Deléglise
Characterizing and detecting spontaneous speech: Application to speaker role recognition. Speech Commun. 56 (2014)
Paul Gay, Elie Khoury, Sylvain Meignier, Jean-Marc Odobez, Paul Deléglise
A conditional random field approach for audio-visual people diarization. ICASSP (2014)
Fethi Bougares, Mickael Rouvier, Nathalie Camelin, Paul Deléglise, Yannick Estève
An Investigation of Single-Pass ASR System Combination for Spoken Language Understanding. SLSP (2013)
Fethi Bougares, Paul Deléglise, Yannick Estève, Mickael Rouvier
LIUM ASR System for ETAPE French Evaluation Campaign: Experiments on System Combination Using Open-Source Recognizers. TSD (2013)
Anthony Rousseau, Paul Deléglise, Yannick Estève
TED-LIUM: an Automatic Speech Recognition dedicated corpus. LREC (2012)
Fethi Bougares, Yannick Estève, Paul Deléglise, Mickael Rouvier, Georges Linarès
Avancées dans le domaine de la transcription automatique par décodage guidé (Improvements on driven decoding system combination) [in French]. JEP-TALN-RECITAL 2012 (2012)
Anthony Rousseau, Fethi Bougares, Paul Deléglise, Holger Schwenk, Yannick Estève
LIUM's systems for the IWSLT 2011 speech translation tasks. IWSLT (2011)
Fethi Bougares, Yannick Estève, Paul Deléglise, Georges Linarès
Bag of n-gram driven decoding for LVCSR system harnessing. ASRU (2011)
Richard Dufour, Yannick Estève, Paul Deléglise
Investigation of Spontaneous Speech Characterization Applied to Speaker Role Recognition. INTERSPEECH (2011)
Antoine Laurent, Sylvain Meignier, Téva Merlin, Paul Deléglise
Computer-assisted transcription of speech based on confusion network reordering. ICASSP (2011)
Richard Dufour, Fethi Bougares, Yannick Estève, Paul Deléglise
Unsupervised model adaptation on targeted speech segments for LVCSR system combination. INTERSPEECH (2010)
Antoine Laurent, Sylvain Meignier, Téva Merlin, Paul Deléglise
Acoustics-based phonetic transcription method for proper nouns. INTERSPEECH (2010)
Anthony Rousseau, Loïc Barrault, Paul Deléglise, Yannick Estève
LIUM's statistical machine translation system for IWSLT 2010. IWSLT (2010)
Richard Dufour, Yannick Estève, Paul Deléglise
Automatic indexing of speech segments with spontaneity levels on large audio database. SSCS@MM (2010)
Paul Deléglise, Yannick Estève, Sylvain Meignier, Téva Merlin
Improvements to the LIUM French ASR system based on CMU sphinx: what helps to significantly reduce the word error rate? INTERSPEECH (2009)
Antoine Laurent, Paul Deléglise, Sylvain Meignier
Grapheme to phoneme conversion using an SMT system. INTERSPEECH (2009)
Richard Dufour, Yannick Estève, Paul Deléglise, Frédéric Béchet
Local and global models for spontaneous speech segment detection and characterization. ASRU (2009)
Antoine Laurent, Téva Merlin, Sylvain Meignier, Yannick Estève, Paul Deléglise
Iterative filtering of phonetic transcriptions of proper nouns. ICASSP (2009)
Antoine Laurent, Téva Merlin, Sylvain Meignier, Yannick Estève, Paul Deléglise
Combined Systems for Automatic Phonetic Transcription of Proper Nouns. LREC (2008)
Yannick Estève, Sylvain Meignier, Paul Deléglise, Julie Mauclair
Extracting true speaker identities from transcriptions. INTERSPEECH (2007)
Julie Mauclair, Yannick Estève, Simon Petit-Renaud, Paul Deléglise
Automatic Detection of Well Recognized Words in Automatic Speech Transcriptions. LREC (2006)
Paul Deléglise, Yannick Estève, Sylvain Meignier, Téva Merlin
The LIUM speech transcription system: a CMU Sphinx III-based system for French broadcast news. INTERSPEECH (2005)
Philippe Daubias, Paul Deléglise
The LIUM-AVS database : a corpus to test lip segmentation and speechreading systems in natural conditions. INTERSPEECH (2003)
Philippe Daubias, Paul Deléglise
Lip-reading based on a fully automatic statistical model. INTERSPEECH (2002)
Philippe Daubias, Paul Deléglise
Statistical Lip-Appearance Models Trained Automatically Using Audio Information. EURASIP J. Adv. Signal Process. 2002 (11) (2002)
Philippe Daubias, Paul Deléglise
Evaluation of an automatically obtained shape and appearance model for automatic audio visual speech recognition. INTERSPEECH (2001)
Alexandrina Rogozan, Paul Deléglise
Adaptive fusion of acoustic and visual sources for automatic speech recognition. Speech Commun. 26 (1-2) (1998)
Alexandrina Rogozan, Paul Deléglise
Hybrid Hidden Markow model / neural network models for speechreading. ESANN (1998)
Alexandrina Rogozan, Paul Deléglise, Mamoun Alissali
Adaptive determination of audio and visual weights for automatic speech recognition. AVSP (1997)
Alexandrina Rogozan, Paul Deléglise
Continuous visual speech recognition using geometric lip-shape models and neural networks. EUROSPEECH (1997)
Paul Deléglise, Alexandrina Rogozan, Mamoun Alissali
Asynchronous integration of audio and visual sources in bi-modal automatic speech recognition. EUSIPCO (1996)
Mamoun Alissali, Paul Deléglise, Alexandrina Rogozan
Asynchronous integration of visual information in an automatic speech recognition system. ICSLP (1996)
Claude Montacié, Paul Deléglise, Frédéric Bimbot, Marie-José Caraty
Cinematic techniques for speech processing: temporal decomposition and multivariate linear prediction. ICASSP (1992)
Frédéric Bimbot, Gérard Chollet, Paul Deléglise
Speech synthesis by structured segments, using temporal decomposition and a glottal excitation. EUROSPEECH (1989)
Frédéric Bimbot, Gérard Chollet, Paul Deléglise, Claude Montacié
Temporal decomposition and acoustic-phonetic decoding of speech. ICASSP (1988)
Paul Deléglise, Frédéric Bimbot, Claude Montacié, Gérard Chollet
Temporal decomposition and acoustic-phonetic decoding for the automatic recognition of continuous speech. ICPR (1988)
Marc Baudry, Paul Deléglise, J.-C. Friedmann
Speech analysis in the time domain using syntactic technics an attempt to formalize the description of phonemes using acoustical cues. ICASSP (1982)