ResearchSpace

Speech rate normalization used to improve speaker verification

Show simple item record

dc.contributor.author Van Heerden, CJ
dc.contributor.author Barnard, E
dc.date.accessioned 2007-07-27T10:22:13Z
dc.date.available 2007-07-27T10:22:13Z
dc.date.issued 2006-11
dc.identifier.citation Van Heerden, CJ and Barnard, E. 2006. Speech rate normalization used to improve speaker verification. 17th Annual Symposium of the Pattern Recognition Association of South Africa, Parys, South Africa, 29 Nov - 1 Dec 2006, pp 6 en
dc.identifier.isbn 978-0-620-37384-5
dc.identifier.uri http://hdl.handle.net/10204/1045
dc.description This paper is published in the SAIEE Africa Research Journal, Vol 98(4), pp 129-135
dc.description.abstract A novel approach to speech rate normalization is presented. Models are constructed to model the way in which speech rate variation of a specific speaker influences the duration of phonemes. The models are evaluated in two ways. Firstly, the mean square error in phoneme duration based on our normalization is compared to the same error when such normalization is not applied. The second evaluation uses the durations of context-dependent phonemes in speaker verification. Both methods show that this approach to normalization is indeed effective to counteract the effect of variable speaking rates. en
dc.language.iso en en
dc.subject Speaker verification en
dc.subject Phoneme en
dc.subject Parametric models en
dc.subject Triphone duration models en
dc.title Speech rate normalization used to improve speaker verification en
dc.type Conference Presentation en
dc.identifier.apacitation Van Heerden, C., & Barnard, E. (2006). Speech rate normalization used to improve speaker verification. http://hdl.handle.net/10204/1045 en_ZA
dc.identifier.chicagocitation Van Heerden, CJ, and E Barnard. "Speech rate normalization used to improve speaker verification." (2006): http://hdl.handle.net/10204/1045 en_ZA
dc.identifier.vancouvercitation Van Heerden C, Barnard E, Speech rate normalization used to improve speaker verification; 2006. http://hdl.handle.net/10204/1045 . en_ZA
dc.identifier.ris TY - Conference Presentation AU - Van Heerden, CJ AU - Barnard, E AB - A novel approach to speech rate normalization is presented. Models are constructed to model the way in which speech rate variation of a specific speaker influences the duration of phonemes. The models are evaluated in two ways. Firstly, the mean square error in phoneme duration based on our normalization is compared to the same error when such normalization is not applied. The second evaluation uses the durations of context-dependent phonemes in speaker verification. Both methods show that this approach to normalization is indeed effective to counteract the effect of variable speaking rates. DA - 2006-11 DB - ResearchSpace DP - CSIR KW - Speaker verification KW - Phoneme KW - Parametric models KW - Triphone duration models LK - https://researchspace.csir.co.za PY - 2006 SM - 978-0-620-37384-5 T1 - Speech rate normalization used to improve speaker verification TI - Speech rate normalization used to improve speaker verification UR - http://hdl.handle.net/10204/1045 ER - en_ZA


Files in this item

Icon
Name: vanHeerden_2006.pdf
Size: 362.3Kb
Format: PDF
View/Open

This item appears in the following Collection(s)

Show simple item record