Application des machines a vecteurs support mono-classe a l'indexation en locuteurs de documents audio - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2006

Application des machines a vecteurs support mono-classe a l'indexation en locuteurs de documents audio

Belkacem Fergani
  • Function : Author
Amrane Houacine
  • Function : Author

Abstract

This paper addresses a new approach based on the Kernel Change Detection algorithm introduced recently by Desobry et al. This new algorithm is applied to the speaker change detection and clustering tasks, which are the key issues in any audio indexing process. We show the efficiency of the method through several experiments using RT'03S NIST data. We discuss also the parameters tuning and compare the results to the well known GLR-BIC algorithm.
Fichier principal
Vignette du fichier
final-28.pdf (86.3 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Loading...

Dates and versions

inria-00119998 , version 1 (12-12-2006)

Identifiers

  • HAL Id : inria-00119998 , version 1

Cite

Belkacem Fergani, Manuel Davy, Amrane Houacine. Application des machines a vecteurs support mono-classe a l'indexation en locuteurs de documents audio. Journees d'Etude sur la Parole 2006, 2006, Dinard, France. ⟨inria-00119998⟩
138 View
281 Download

Share

Gmail Facebook Twitter LinkedIn More