Multi-stage speaker diarization of broadcast news - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Audio, Speech and Language Processing Année : 2006

Multi-stage speaker diarization of broadcast news

Résumé

Abstract: This paper describes recent advances in speaker diarization with a multistage segmentation and clustering system, which incorporates a speaker identification step. This system builds upon the baseline audio partitioner used in the LIMSI broadcast news transcription system. The baseline partitioner provides a high cluster purity, but has a tendency to split data from speakers with a large quantity of data into several segment clusters. Several improvements to the baseline system have been made. First, the iterative Gaussian mixture model (GMM) clustering has been replaced by a Bayesian information criterion (BIC) agglomerative clustering. Second, an additional clustering stage has been added, using a GMM-based speaker identification method. Finally, a post-processing stage refines the segment boundaries using the output of a transcription system. On the National Institute of Standards and Technology (NIST) RT-04F and ESTER evaluation data, the multistage system reduces the speaker error by over 70% relative to the baseline system, and gives between 40% and 50% reduction relative to a single-stage BIC clustering system
Fichier principal
Vignette du fichier
sap_rt_diarization.pdf (315.51 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01434241 , version 1 (22-03-2017)

Identifiants

Citer

Claude Barras, Xuan Zhu, Sylvain Meignier, Jean-Luc Gauvain. Multi-stage speaker diarization of broadcast news. IEEE Transactions on Audio, Speech and Language Processing, 2006, 14 (5), ⟨10.1109/TASL.2006.878261⟩. ⟨hal-01434241⟩
208 Consultations
623 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More