Ajout de nouveaux noms propres au vocabulaire d’un système de transcription en utilisant un corpus diachronique [Adding proper names to the vocabulary of a speech transcription system using a contemporary diachronic corpus]

Les noms propres sont souvent indispensables pour comprendre l’information contenue dans un document. Notre travail se concentre sur l’augmentation automatique du vocabulaire d’un systeme de transcription automatique de la parole (RAP) a partir d’un corpus diachronique. Nous faisons l’hypothese que certains noms propres apparaissent dans des documents relatifs a la meme periode temporelle et dans des contextes lexicaux similaires. Trois methodes de selection de noms propres sont proposees pour augmenter de facon dynamique le vocabulaire en utilisant des informations lexicales et temporelles. Les methodes sont fondees sur des statistiques de cooccurrences dans des fenetres de taille fixe, sur l’information mutuelle et sur le modele vectoriel. Differents parametres de selection de noms propres sont egalement etudies afin de limiter l’augmentation du vocabulaire. Les resultats de reconnaissance montrent une reduction significative du taux d’erreur de noms propres en utilisant un vocabulaire augmente.

[1]  Alan W. Black,et al.  Letter to sound rules for accented lexicon compression , 1998, ICSLP.

[2]  François Yvon,et al.  Les noms propres en traitement automatique de la parole , 2000 .

[3]  Guillaume Gravier,et al.  The ester 2 evaluation campaign for the rich transcription of French radio broadcasts , 2009, INTERSPEECH.

[4]  Irina Illina,et al.  The automatic news transcription system: ANTS, some real time experiments , 2004, INTERSPEECH.

[5]  Jean-Luc Gauvain,et al.  Unsupervised language model adaptation for broadcast news , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[6]  Jerome R. Bellegarda,et al.  Statistical language model adaptation: review and perspectives , 2004, Speech Commun..

[7]  Alexandre Allauzen,et al.  Diachronic vocabulary adaptation for broadcast news transcription , 2005, INTERSPEECH.

[8]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[9]  Guy Perennou,et al.  BDLEX: a lexicon for spoken and written french , 1998, LREC.

[10]  Tatsuya Kawahara,et al.  Recent Development of Open-Source Speech Recognition Engine Julius , 2009 .

[11]  Georges Linarès,et al.  Person name recognition in ASR outputs using continuous context models , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[12]  Marcello Federico,et al.  Broadcast news LM adaptation over time , 2004, Comput. Speech Lang..

[13]  Georges Linarès,et al.  Exploring temporal context in diachronic text documents for automatic OOV proper name retrieval , 2013, LTC 2013.

[14]  Kenneth Ward Church,et al.  Word Association Norms, Mutual Information, and Lexicography , 1989, ACL.

[15]  Mark Dredze,et al.  Contextual Information Improves OOV Detection in Speech , 2010, NAACL.

[16]  Georges Linarès,et al.  Local Methods for On-Demand Out-of-Vocabulary Word Retrieval , 2008, LREC.

[17]  Helmut Schmidt,et al.  Probabilistic part-of-speech tagging using decision trees , 1994 .

[18]  Gerard Salton,et al.  A vector space model for automatic indexing , 1975, CACM.

[19]  Alexander H. Waibel,et al.  Reducing the OOV rate in broadcast news speech recognition , 1998, ICSLP.

[20]  Søren Riis,et al.  Self-organizing letter code-book for text-to-phoneme neural network model , 2000, INTERSPEECH.

[21]  Ciro Martins,et al.  Dynamic language modeling for European Portuguese , 2010, Comput. Speech Lang..

[22]  Katsutoshi Ohtsuki,et al.  Unsupervised vocabulary expansion for automatic transcription of broadcast news , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[23]  Marcello Federico,et al.  Lexicon adaptation for broadcast news transcription , 2001 .

[24]  Alex Waibel,et al.  New developments in automatic meeting transcription , 2000, INTERSPEECH.

[25]  Denis Jouvet,et al.  Evaluating grapheme-to-phoneme converters in automatic speech recognition context , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[26]  Georges Linarès,et al.  Combining acoustic name spotting and continuous context models to improve spoken person name recognition in speech , 2013, INTERSPEECH.

[27]  Christopher D. Manning,et al.  Introduction to Information Retrieval , 2010, J. Assoc. Inf. Sci. Technol..

[28]  Kazuo Onoe,et al.  Time dependent language model for broadcast news transcription and its post-correction , 1998, ICSLP.

[29]  Hermann Ney,et al.  Joint-sequence models for grapheme-to-phoneme conversion , 2008, Speech Commun..

[30]  Denis Maurel,et al.  Textual Similarity based on Proper Names , 2002 .

[31]  Andreas Stolcke,et al.  SRILM - an extensible language modeling toolkit , 2002, INTERSPEECH.

[32]  Denyse Baillargeon,et al.  Bibliographie , 1929 .

[33]  Paul Taylor,et al.  Hidden Markov models for grapheme to phoneme conversion , 2005, INTERSPEECH.

[34]  Georges Linarès,et al.  Extension du vocabulaire d’un système de transcription avec de nouveaux noms propres en utilisant un corpus diachronique , 2014 .

[35]  K. Ohtsuki,et al.  Incremental language modeling for broadcast news , 2005, IEEE Workshop on Automatic Speech Recognition and Understanding, 2005..

[36]  Denis Jouvet,et al.  Grapheme-to-Phoneme Conversion Using Conditional Random Fields , 2011, INTERSPEECH.