Speaker diarization: about whom the speaker is talking? - Archive ouverte HAL Access content directly
Conference Papers Year : 2006

Speaker diarization: about whom the speaker is talking?

Abstract

The automatic speaker diarization consists in splitting the signal into homogeneous segments and clustering them by speakers. However the speaker segments are specified with anonymous labels. This pa- per proposed a solution to identify those speakers by extracting their full names pronounced in the show. With a semantic classification tree automatically built on a training corpus, the full names detected in transcription of a segment are associated to this segment or to one of its neighbors. Then, a merging method allows to associate a full name to a speaker cluster instead of a anonymous label provided by the diarization. The experiments are carried out over French broadcast news records from the ESTER 2005 evaluation campaign. About 70% show duration is correctly processed for both development and eval- uation corpora. On the evaluation corpus, 18.15% show duration is wrongly named and no decision is taken for 11.91% show duration.
Fichier principal
Vignette du fichier
odyssey.pdf (325.62 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01434121 , version 1 (09-02-2017)

Identifiers

  • HAL Id : hal-01434121 , version 1

Cite

Julie Mauclair, Sylvain Meignier, Yannick Estève. Speaker diarization: about whom the speaker is talking?. IEEE Speaker Odyssey 2006, 2006, San Juan Puerto Rico. ⟨hal-01434121⟩
479 View
267 Download

Share

Gmail Facebook X LinkedIn More