Comparison of Speaker Adaptation Methods as Feature Extraction for SVM-Based Speaker Recognition

Abstract : In the last years the speaker recognition field has made extensive use of speaker adaptation techniques. Adaptation allows speaker model parameters to be estimated using less speech data than needed for maximum likelihood (ML) training. The Maximum-A-Posteriori (MAP) and Maximum Likelihood Linear Regression (MLLR) techniques have typically been used for adaptation. Recently, MAP and MLLR adaptation have been incorporated in the feature extraction stage of Support Vector Machine (SVM) based speaker recognition systems. Two approaches to feature extraction use a SVM to classify either the MAP-adapted Gaussian mean vector parameters (GSV-SVM) or the Maximum-Likelihood Linear Regression (MLLR) transform coefficients (MLLR-SVM). In this paper we provide an experimental analysis of the GSV-SVM and MLLR-SVM approaches. We largely focus on the latter by exploring constrained and unconstrained transforms and different choices of the acoustic model. A channel-compensated front-end is used to prevent the MLLR transforms to adapt to channel components in the speech data. Additional acoustic models were trained using Speaker Adaptive Training (SAT) to better estimate the speaker MLLR transforms. We provide results on the NIST 2005 and 2006 Speaker Recognition Evaluation (SRE) data and fusion results on the SRE 2006 data. The results show that using the compensated front-end, SAT models and multiple regression classes bring major performance improvements.
Document type :
Journal articles
Complete list of metadatas

Cited literature [31 references]  Display  Hide  Download
Contributor : Claude Barras <>
Submitted on : Monday, January 22, 2018 - 10:51:24 PM
Last modification on : Tuesday, September 17, 2019 - 1:13:56 AM
Long-term archiving on : Thursday, May 24, 2018 - 11:11:42 AM


Files produced by the author(s)




Marc Ferràs, Cheung-Chi Leung, Claude Barras, Jean-Luc Gauvain. Comparison of Speaker Adaptation Methods as Feature Extraction for SVM-Based Speaker Recognition. IEEE Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2010, 18 (6), pp.1366 - 1378. ⟨10.1109/TASL.2009.2034187⟩. ⟨hal-01690338⟩



Record views


Files downloads