Using confidence measure for keyword detection in continuous speech recognition

Abstract : This paper deals with the problem of detection keywords/rejection out-of-vocabulary in continuous speech recognition. Two different techniques based on confidence measures are investigated to improve the detection of keywords using a grammar founded on loop of phones. Confidence measures are computed from phone level information provided by a Hidden Markov model based speech recognizer. We use two kinds of likelihood as ratio and distance, and theirs normalised forms to compute a confidence measures for each word. All confidence measures are are evaluated using the French SPEECHDAT database. The Figure-Of-Merite (FOM) for the normalized likelihood ratio is about $68.2\%$ compared to $71.5\%$ obtained by the normalized likelihood distance
Type de document :
Communication dans un congrès
Conférence Internationale sur l'accès Intelligent aux Documents Multimédia sur l'Internet - Medinet'04, 2004, Tozeur, Tunisie, 10 p, 2004
Liste complète des métadonnées

https://hal.inria.fr/inria-00100205
Contributeur : Publications Loria <>
Soumis le : mardi 26 septembre 2006 - 10:15:29
Dernière modification le : jeudi 11 janvier 2018 - 06:19:55

Identifiants

  • HAL Id : inria-00100205, version 1

Citation

Yassine Benayed, Dominique Fohr, Jean-Paul Haton, Gérard Chollet. Using confidence measure for keyword detection in continuous speech recognition. Conférence Internationale sur l'accès Intelligent aux Documents Multimédia sur l'Internet - Medinet'04, 2004, Tozeur, Tunisie, 10 p, 2004. 〈inria-00100205〉

Partager

Métriques

Consultations de la notice

254