Improved GMM-based speaker verification using SVM-driven impostor dataset selection
Data(s) |
2009
|
---|---|
Resumo |
The problem of impostor dataset selection for GMM-based speaker verification is addressed through the recently proposed data-driven background dataset refinement technique. The SVM-based refinement technique selects from a candidate impostor dataset those examples that are most frequently selected as support vectors when training a set of SVMs on a development corpus. This study demonstrates the versatility of dataset refinement in the task of selecting suitable impostor datasets for use in GMM-based speaker verification. The use of refined Z- and T-norm datasets provided performance gains of 15% in EER in the NIST 2006 SRE over the use of heuristically selected datasets. The refined datasets were shown to generalise well to the unseen data of the NIST 2008 SRE. |
Formato |
application/pdf |
Identificador | |
Publicador |
International Speech Communication Association (ISCA) |
Relação |
http://eprints.qut.edu.au/29484/1/29484.pdf http://www.interspeech2009.org/ McLaren, Mitchell L., Vogt, Robert J., Baker, Brendan J., & Sridharan, Sridha (2009) Improved GMM-based speaker verification using SVM-driven impostor dataset selection. In Proceedings of Interspeech 2009, International Speech Communication Association (ISCA), Brighton Centre, Brighton, pp. 1267-1270. |
Direitos |
Copyright 2009 International Speech Communication Association |
Fonte |
Faculty of Built Environment and Engineering; Information Security Institute; School of Engineering Systems |
Palavras-Chave | #Speaker recognition #Data selection #Support vector machines #Gaussian Mixture Models |
Tipo |
Conference Paper |