Improving the Performance of a Keyword Spotting System by Using Support Vector Machines - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2003

Improving the Performance of a Keyword Spotting System by Using Support Vector Machines

Dominique Fohr
Gérard Chollet

Résumé

Support Vector Machines (SVM) represent a new approach to pattern classification developed from the theory of structural risk minimisation. In this paper, we propose an investigation into the application of SVM to the confidence measurement problem in speech recognition. Confidence measures are computed using the phone level information provided by a Hidden Markov Model (HMM) based speech recognizer. We use three kinds of average techniques as arithmetic, geometric and harmonic averages in order to compute a confidence measure for each word. The acceptance/rejection decision for a given word is based on the confidence feature vector which is processed by a SVM classifier. The performance of the proposed SVM classifier is compared with methods based on the averaging of phone confidence measures.
Fichier non déposé

Dates et versions

inria-00099708 , version 1 (26-09-2006)

Identifiants

  • HAL Id : inria-00099708 , version 1

Citer

Yassine Benayed, Dominique Fohr, Jean-Paul Haton, Gérard Chollet. Improving the Performance of a Keyword Spotting System by Using Support Vector Machines. IEEE Automatic Speech Recognition and Understanding Workshop - ASRU'2003, Dec 2003, St. Thomas, U.S. Virgin islands, 5 p. ⟨inria-00099708⟩
89 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More