A Language-identification inspired method for spontaneous speech detection

Abstract : Most of spontaneous speech detection systems relies on dis-fluency analysis or on combination of acoustic and linguistic features. This paper presents a method that considers spontaneous speech as a specific language, which could be identified by using language-recognition methods, such as shifted delta cepstrum parameters, dimensionality reduction by linear dis-criminant analysis and factor-analysis based filtering process. Experiments are conducted on the French EPAC corpus. On a 3 spontaneity-level task, this approach obtains a relative gain of about 22% of identification rates, in comparison to the classical MFCC/GMM technique. Then, we combine these techniques to others previously proposed for spontaneous speech detection. Finally, the proposed system obtains a recognition rate of 65% on high spontaneous speech segments.
Type de document :
Communication dans un congrès
INTERSPEECH, Sep 2010, Makuhari, Japan
Liste complète des métadonnées

Contributeur : Bibliothèque Universitaire Déposants Hal-Avignon <>
Soumis le : lundi 23 mai 2016 - 15:04:49
Dernière modification le : mardi 5 mars 2019 - 01:39:16


  • HAL Id : hal-01320176, version 1



Mickael Rouvier, Richard Dufour, Georges Linarès, Yannick Estève. A Language-identification inspired method for spontaneous speech detection. INTERSPEECH, Sep 2010, Makuhari, Japan. 〈hal-01320176〉



Consultations de la notice