Evolutive HMM for Multi-Speaker Tracking System - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2000

Evolutive HMM for Multi-Speaker Tracking System

Sylvain Meignier
Corinne Fredouille
Teva Merlin

Résumé

Seeking within a speech sequence the speaker utterances is one of the main tasks of indexing. In this paper, the proposed speaker tracking system is defined in the case where all speaker identities are known beforehand. The conversation is modeled as an evolutive HMM-like model, in which speaker models computed are added one by one.A temporary indexing is proposed after each speaker adding and then challenged at the next step. This process is iterated until all the speakers are detected. The system has been assessed using multi-speaker messages generated by concatenation of Switchboard mono-speaker segments. The obtained results show the potentiality of the proposed solution.
Fichier principal
Vignette du fichier
icassp2000.pdf (3.91 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01451542 , version 1 (22-03-2017)

Identifiants

  • HAL Id : hal-01451542 , version 1

Citer

Sylvain Meignier, Jean-François Bonastre, Corinne Fredouille, Teva Merlin. Evolutive HMM for Multi-Speaker Tracking System. International Conference on Acoustics Speech and Signal Processing (ICASSP 2000), IEEE, 2000, Istanbul, Turkey. pp.4. ⟨hal-01451542⟩

Collections

UNIV-AVIGNON LIA
104 Consultations
54 Téléchargements

Partager

Gmail Facebook X LinkedIn More