Combining transcription-based and acoustic-based speaker identifications for broadcast news - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

Combining transcription-based and acoustic-based speaker identifications for broadcast news

Résumé

In this paper, we consider the issue of speaker identification within audio records of broadcast news. The speaker identity information is extracted from both transcript-based and acoustic-based speaker identification systems. This information is combined in the belief functions framework, which makes coherent the knowledge representation of the problem. The Kuhn-Munkres algorithm is used to optimize the assignment problem of speaker identities and speaker clusters. Experiments carried out on French broadcast news from the French evaluation campaign ESTER show the efficiency of the proposed combination method.
Fichier principal
Vignette du fichier
Khoury_ICASSP_2012.pdf (256.25 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01433486 , version 1 (03-04-2017)

Identifiants

Citer

Elie El Khoury, Antoine Laurent, Sylvain Meignier, Simon Petitrenaud. Combining transcription-based and acoustic-based speaker identifications for broadcast news. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2012), 2012, Kyoto, Japan. pp.4377 - 4380, ⟨10.1109/ICASSP.2012.6288889⟩. ⟨hal-01433486⟩
124 Consultations
105 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More