DocumentCode :
2178954
Title :
The SRI NIST 2010 speaker recognition evaluation system
Author :
Scheffer, Nicolas ; Ferrer, Luciana ; Graciarena, Martin ; Kajarekar, Sachin ; Shriberg, Elizabeth ; Stolcke, Andreas
Author_Institution :
SRI Int., Menlo Park, CA, USA
fYear :
2011
fDate :
22-27 May 2011
Firstpage :
5292
Lastpage :
5295
Abstract :
The SRI speaker recognition system for the 2010 NIST speaker recognition evaluation (SRE) incorporates multiple subsystems with a variety of features and modeling techniques. We describe our strategy for this year´s evaluation, from the use of speech recognition and speech segmentation to the individual system descriptions as well as the final combination. Our results show that under most conditions, the cepstral systems tend to perform the best, but that other, non-cepstral systems have the most complementarity. The combination of several subsystems with the use of adequate side information gives a 35% improvement on the standard telephone condition. We also show that a constrained cepstral system based on nasal syllables tends to be more robust to vocal effort variabilities.
Keywords :
speaker recognition; SRE; SRI NIST 2010 speaker recognition evaluation system; cepstral systems; speech recognition; speech segmentation; Indexes; Mixers; high-level modeling; prosody; speaker recognition; system fusion;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on
Conference_Location :
Prague
ISSN :
1520-6149
Print_ISBN :
978-1-4577-0538-0
Electronic_ISBN :
1520-6149
Type :
conf
DOI :
10.1109/ICASSP.2011.5947552
Filename :
5947552
Link To Document :
بازگشت