Benoit Habert

Also published as: B. Habert, Benoît Habert


Annotation and analysis of overlapping speech in political interviews
Martine Adda-Decker | Claude Barras | Gilles Adda | Patrick Paroubek | Philippe Boula de Mareüil | Benoit Habert
Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08)

Looking for a better understanding of spontaneous speech-related phenomena and to improve automatic speech recognition (ASR), we present here a study on the relationship between the occurrence of overlapping speech segments and disfluencies (filled pauses, repetitions, revisions) in political interviews. First we present our data, and our overlap annotation scheme. We detail our choice of overlapping tags and our definition of disfluencies; the observed ratios of the different overlapping tags are examined, as well as their correlation with of the speaker role and propose two measures to characterise speakers’ interacting attitude: the attack/resist ratio and the attack density. We then study the relationship between the overlapping speech segments and the disfluencies in our corpus, before concluding on the perspectives that our experiments offer.


Highlighting Latent Structure in Documents
H. Folch | B. Habert | M. Jardino | N. Pernelle | M.C. Rousset | A. Termier
Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04)

Automatic Audio and Manual Transcripts Alignment, Time-code Transfer and Selection of Exact Transcripts
C. Barras | G. Adda | M. Adda-Decker | B. Habert | P. Boula de Mareüil | P. Paroubek
Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04)

The present study focuses on automatic processing of sibling resources of audio and written documents, such as available in audio archives or for parliament debates: written texts are close but not exact audio transcripts. Such resources deserve attention for several reasons: they represent an interesting testbed for studying differences between written and spoken material and they yield low cost resources for acoustic model training. When automatically transcribing the audio data, regions of agreement between automatic transcripts and written sources allow to transfer time-codes to the written documents: this may be helpful in an audio archive or audio information retrieval environment. Regions of disagreement can be automatically selected for further correction by human transcribers. This study makes use of 10 hours of French radio interview archives with corresponding press-oriented transcripts. The audio corpus has then been transcribed using the LIMSI speech recognizer resulting in automatic transcripts, exhibiting an average word error rate of 12%. 80% of the text corpus (with word chunks of at least five words) can be exactly aligned with the automatic transcripts of the audio data. The residual word error rate on these 80% is less than 1%.


TyPTex: Inductive Typological Text Classification by Multivariate Statistical Analysis for NLP Systems Tuning/Evaluation
Helka Folch | Serge Heiden | Benoît Habert | Serge Fleury | Gabriel Illouz | Pierre Lafon | Julien Nioche | Sophie Prévost
Proceedings of the Second International Conference on Language Resources and Evaluation (LREC’00)


Symbolic word clustering for medium-size corpora
Benoit Habert | Elie Naulleau | Adeline Nazarenko
COLING 1996 Volume 1: The 16th International Conference on Computational Linguistics


Using Inheritance in Object-Oriented Programming to Combine Syntactic Rules and Lexical Idiosyncrasies
Benoît Habert
Proceedings of the Second International Workshop on Parsing Technologies

In parsing idioms and frozen expressions in French, one needs to combine general syntactic rules and idiosyncratic constraints. The inheritance structure provided by Object-Oriented Programming languages, and more specifically the combination of methods present in CLOS, Common Lisp Object System, appears as an elegant and efficient approach to deal with such a complex interaction.