Ecole d'ingénieur et centre de recherche en Sciences du numérique

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

Evans, Nicholas; Fredouille, Corinne; Bonastre, Jean-François

ICASSP 2009, International conference on Acoustics, Speech and Signal Processing, April 19-24, 2009, Taipei, Taiwan

            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 onetheless 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 Doi Hal Bibtex

Titre:Speaker diarization using unsupervised discriminant analysis of inter-channel delay features
Mots Clés:Speaker diarization, multiple distant microphones
Type:Conférence
Langue:English
Ville:Taipei
Pays:TAÏWAN, PROVINCE DE CHINE
Date:
Département:Sécurité numérique
Eurecom ref:2654
Copyright: © 2009 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Bibtex: @inproceedings{EURECOM+2654, doi = { http://dx.doi.org/10.1109/ICASSP.2009.4960520}, year = {2009}, title = {{S}peaker diarization using unsupervised discriminant analysis of inter-channel delay features}, author = {{E}vans, {N}icholas and {F}redouille, {C}orinne and {B}onastre, {J}ean-{F}ran{\'c}ois}, booktitle = {{ICASSP} 2009, {I}nternational conference on {A}coustics, {S}peech and {S}ignal {P}rocessing, {A}pril 19-24, 2009, {T}aipei, {T}aiwan}, address = {{T}aipei, {TA}{\"{I}}{WAN}, {PROVINCE} {DE} {CHINE}}, month = {04}, url = {http://www.eurecom.fr/publication/2654} }
Voir aussi: