Fiche du document
17 mai 2010
- ISIDORE Id: 10670/1.959371...
- hal: hal-01393609
HALSHS : archive ouverte en Sciences de l’Homme et de la Société - notices sans texte intégral
http://hal.archives-ouvertes.fr/licences/copyright/ , info:eu-repo/semantics/OpenAccess
Sujets proches
Talking Natural science Sciences Science of science Syllable Language and languages--Syllable Frenchmen (French people)Citer ce document
Brigitte Bigi et al., « Automatic detection of syllable boundaries in spontaneous speech », HALSHS : archive ouverte en Sciences de l’Homme et de la Société - notices sans texte intégral, ID : 10670/1.959371...
Métriques
Partage / Export
Résumé
This paper presents the outline and performance of an automatic syllable boundary detection system. The syllabification of phonemes is performed with a rule-based system, implemented in a Java program. Phonemes are categorized into 6 classes and specific rules are developed to deal with a French spontaneous speech corpus. Moreover, the proposed phonemes, classes and rules are listed in an external configuration file of the tool (under GPL licence). Finally, performances are evaluated and compared to state-of-the-art systems and show significant improvements.
