QUT speaker identity verification system for EVALITA 2009
| Data(s) |
2009
|
|---|---|
| Resumo |
This document outlines the system submitted by the Speech and Audio Research Laboratory at the Queensland University of Technology (QUT) for the Speaker Identity Verication: Application task of EVALITA 2009. This submission consisted of a score-level fusion of three component systems, a joint-factor GMM system and two SVM systems using GLDS and GMM supervector kernels. Development and evaluation results are presented, demonstrating the effectiveness of this fused system approach. |
| Formato |
application/pdf |
| Identificador | |
| Relação |
http://eprints.qut.edu.au/32228/1/c32228.pdf http://www.aixia09.unimore.it/ McLaren, Mitchell L., Vogt, Robert J., Baker, Brendan J., & Sridharan, Sridha (2009) QUT speaker identity verification system for EVALITA 2009. In Proceedings of the 11th Conference of the Italian Association for Artificial Intelligence, Reggio Emilia. |
| Direitos |
Copyright 2009 [please consult the authors] |
| Fonte |
Faculty of Built Environment and Engineering; School of Engineering Systems |
| Palavras-Chave | #080104 Computer Vision #Speaker Identity Verification #EVALITA 2009 |
| Tipo |
Conference Paper |
