Segmentation selon le locuteur : les activités du consortium ELISA dans le cadre de Nist RT03

Abstract : This paper presents the ELISA consortium activities in automatic speaker diarization (also known as speaker segmentation) during the NIST Rich Transcription (RT) 2003 evaluation. The experiments were achieved on real broadcast news data (HUB4), in the framework of the ELISA consortium. The paper firstly shows the interest of segmentation in acoustic macro classes (like gender or bandwidth) as a front-end processing for segmentation/diarization task. The impact of this prior acoustic segmentation is evaluated in terms of speaker diarization performance. Secondly, two different approaches from CLIPS and LIA laboratories are presented and different possibilities of combining them are investigated. The system submitted as ELISA primary obtained the second lower diarization error rate compared to the other RT03-participant primary systems. Another ELISA system submitted as secondary outperformed the best primary system (i.e. it obtained the lowest speaker diarization error rate).
Document type :
Conference papers
Complete list of metadatas

Cited literature [9 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01434484
Contributor : Sylvain Meignier <>
Submitted on : Tuesday, March 28, 2017 - 2:17:44 PM
Last modification on : Monday, July 8, 2019 - 3:10:54 PM
Long-term archiving on : Thursday, June 29, 2017 - 4:10:22 PM

File

Moraru-Meignier-etal.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : hal-01434484, version 1

Citation

Daniel Moraru, Sylvain Meignier, Corinne Fredouille, Laurent Besacier, Jean-François Bonastre. Segmentation selon le locuteur : les activités du consortium ELISA dans le cadre de Nist RT03. Journées d'Etude sur la Parole (JEP 2004), AFCP, Apr 2004, Fès, Maroc. pp.4. ⟨hal-01434484⟩

Share

Metrics

Record views

227

Files downloads

54