Skip to Main content Skip to Navigation
Conference papers

Etude pour l’amélioration d’un système d’identification nommée du locuteur

Abstract : Automatic speaker segmentation and classification produce generic labels rather than the true identity of the speakers. The proposed approach is based on the use of a semantic classification tree using lexical rules to extract the true identity of the speakers from the transcription. In this paper, experiments are carried out on French broadcast news from ESTER 2005 to evaluate this approach, focusing on the impact of the various combinations of automatic vs. manual transcription with automatic vs. manual speaker segmenta-tion/classification. We also study the errors generated by the system.
Complete list of metadatas

Cited literature [9 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00412340
Contributor : Christine Jacquin <>
Submitted on : Monday, April 3, 2017 - 10:24:15 PM
Last modification on : Thursday, April 5, 2018 - 10:36:49 AM
Document(s) archivé(s) le : Tuesday, July 4, 2017 - 2:58:27 PM

File

028_jep_1651.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : hal-00412340, version 1

Citation

Vincent Jousse, Christine Jacquin, Sylvain Meignier, Yannick Estève, Béatrice Daille. Etude pour l’amélioration d’un système d’identification nommée du locuteur. Journées d'Etude de la Parole, Jun 2008, Avignon, France. pp.10. ⟨hal-00412340⟩

Share

Metrics

Record views

182

Files downloads

40