THE SRI NIST 2008 speaker recognition evaluation system

The SRI speaker recognition system for the 2008 NIST speaker recognition evaluation (SRE) incorporates a variety of models and features, both cepstral and stylistic. We highlight the improvements made to specific subsystems and analyze the performance of various subsystem combinations in different data conditions. We show the importance of language and nativeness conditioning, as well as the role of ASR for speaker verification.

• Type: Conference
• Year: 2009
• Where: ICASSP
• Authors: Sachin S. Kajarekar, Nicolas Scheffer, Martin Graciarena, Elizabeth Shriberg, Andreas Stolcke, Luciana Ferrer, Tobias Bocklet
• Keywords: ICASSP 2009, NIST Speaker Recognition, Signal Processing, Speaker Recognition, SRI Speaker Recognition