Speaker diarization using unsupervised discriminant analysis of inter-channel delay features

Abstract : When multiple microphones are available estimates of inter-channel delay, which characterise a speaker's location, can be used as features for speaker diarization. Background noise and reverberation can, however, lead to noisy features and poor performance. To ameliorate these problems, this paper presents a new approach to the discriminant analysis of delay features for speaker diarization. This novel and nonetheless unsupervised approach aims to increase speaker separability in delay-space. We assess the approach on subsets of four standard NIST RT datasets and demonstrate a relative improvement in diarization error rate of 25% on a separate evaluation set using delay features alone.
Document type :
Conference papers
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01318388
Contributor : Bibliothèque Universitaire Déposants Hal-Avignon <>
Submitted on : Thursday, May 19, 2016 - 3:23:58 PM
Last modification on : Friday, March 29, 2019 - 2:36:04 PM

Identifiers

Collections

Citation

Nicholas Evans, Corinne Fredouille, Jean-François Bonastre. Speaker diarization using unsupervised discriminant analysis of inter-channel delay features. IACSSP'09, Apr 2009, Taipei, Taiwan. ⟨10.1109/ICASSP.2009.4960520⟩. ⟨hal-01318388⟩

Share

Metrics

Record views

52