Skip to Main content Skip to Navigation
Conference papers

I-vectors and ILP clustering adapted to cross-show speaker diarization

Abstract : We propose to study speaker diarization from a collection of audio documents. The goal is to detect speakers appearing in several shows. In our approach, each show of the collection is processed separately before being processed collectively , to group speakers involved in several shows. Two clustering methods are studied for the overall processing of the collection: one uses the NCLR metric and the other is inspired by techniques based on i-vectors, mainly used in the speaker verification field. Both methods were evaluated on the whole training corpus of ESTER 2. The method based on the use of i-vectors achieves error rates similar to those obtained by the NCLR method, however, the computation time is on average 8.66 times faster. Therefore, this method is suitable for processing large volumes of data.
Complete list of metadatas

Cited literature [9 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01450711
Contributor : Hakim Amokrane <>
Submitted on : Monday, April 3, 2017 - 9:50:48 PM
Last modification on : Thursday, April 6, 2017 - 10:00:10 AM
Document(s) archivé(s) le : Tuesday, July 4, 2017 - 2:52:13 PM

File

i12_2174.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : hal-01450711, version 1

Collections

Citation

Grégor Dupuy, Mickael Rouvier, Sylvain Meignier, Yannick Estève. I-vectors and ILP clustering adapted to cross-show speaker diarization. Interspeech, 2012, Portland, Oregon (USA), United States. ⟨hal-01450711⟩

Share

Metrics

Record views

186

Files downloads

89