Frame-Synchronous And Local Confidence Measures For On-The-Fly Keyword Spotting

Joseph Razik 1 Odile Mella 1 Dominique Fohr 1 Jean-Paul Haton 1
1 PAROLE - Analysis, perception and recognition of speech
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : This paper presents several new confidence measures for speech recognition applications. The major advantage of these measures is that they can be evaluated with only a part of the whole sentence. Two of these measures can be computed directly within the first step of the recognition process, synchronously with the decoding engine. Such measures are useful to drive the recognition process by modifying the likelihood score or to validate recognized words in on-the-fly applications as keyword spotting task and on-line automatic speech transcription for deaf people. Two kinds of results are given. Firstly, an EER evaluation on a French broadcast news corpus shows performance close to the batch version of these measures (23.9% against 23.8% of EER). Secondly, for the keyword spotting application, our best measure provides a decrease of the false-acceptation rate by 50% with only a decrease of the correct words by 5%.
Type de document :
Communication dans un congrès
International Symposium on Signal Processing and its Applications - ISSPA 2007, Feb 2007, Sharjah, United Arab Emirates. IEEE, pp.1-4, 2007
Liste complète des métadonnées

https://hal.inria.fr/inria-00134135
Contributeur : Joseph Razik <>
Soumis le : mercredi 28 février 2007 - 17:22:03
Dernière modification le : jeudi 11 janvier 2018 - 06:19:56

Identifiants

  • HAL Id : inria-00134135, version 1

Collections

Citation

Joseph Razik, Odile Mella, Dominique Fohr, Jean-Paul Haton. Frame-Synchronous And Local Confidence Measures For On-The-Fly Keyword Spotting. International Symposium on Signal Processing and its Applications - ISSPA 2007, Feb 2007, Sharjah, United Arab Emirates. IEEE, pp.1-4, 2007. 〈inria-00134135〉

Partager

Métriques

Consultations de la notice

217