Improving PLDA speaker verification using WMFD and linear-weighted approaches in limited microphone data conditions
Data(s) |
10/09/2015
|
---|---|
Resumo |
This paper proposes the addition of a weighted median Fisher discriminator (WMFD) projection prior to length-normalised Gaussian probabilistic linear discriminant analysis (GPLDA) modelling in order to compensate the additional session variation. In limited microphone data conditions, a linear-weighted approach is introduced to increase the influence of microphone speech dataset. The linear-weighted WMFD-projected GPLDA system shows improvements in EER and DCF values over the pooled LDA- and WMFD-projected GPLDA systems in inter-view-interview condition as WMFD projection extracts more speaker discriminant information with limited number of sessions/ speaker data, and linear-weighted GPLDA approach estimates reliable model parameters with limited microphone data. |
Formato |
application/pdf |
Identificador | |
Publicador |
Interspeech 2015 |
Relação |
http://eprints.qut.edu.au/85082/1/Improving%20PLDA%20Speaker%20Verification%20using%20WMFD%20and%20Linear-weighted%20Approaches%20in%20Limited%20Microphone%20Data%20Conditions.pdf http://www.isca-speech.org/archive/interspeech_2015/i15_2332.html Kanagasundaram, Ahilan, Dean, David B., & Sridharan, Sridha (2015) Improving PLDA speaker verification using WMFD and linear-weighted approaches in limited microphone data conditions. In Proceedings of the 16th Annual Conference of the International Speech Communication Association, Interspeech 2015, Interspeech 2015, Dresden, Germany, pp. 2332-2336. http://purl.org/au-research/grants/ARC/LP130100110 |
Direitos |
Copyright 2015 [Please consult the author] |
Fonte |
School of Electrical Engineering & Computer Science; Faculty of Science and Technology; Information Security Institute |
Palavras-Chave | #090600 ELECTRICAL AND ELECTRONIC ENGINEERING #090609 Signal Processing #109900 OTHER TECHNOLOGY #speaker verification #i-vectors #GPLDA #WMFD #linear-weighted |
Tipo |
Conference Paper |