DocumentCode :
3528719
Title :
THE SRI NIST 2008 speaker recognition evaluation system
Author :
Kajarekar, Sachin S. ; Scheffer, Nicolas ; Graciarena, Martin ; Shriberg, Elizabeth ; Stolcke, Andreas ; Ferrer, Luciana ; Bocklet, Tobias
Author_Institution :
SRI Int., Menlo Park, CA
fYear :
2009
fDate :
19-24 April 2009
Firstpage :
4205
Lastpage :
4208
Abstract :
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.
Keywords :
natural language processing; speaker recognition; language conditioning; nativeness conditioning; speaker recognition evaluation system; speaker verification; Automatic speech recognition; Cepstral analysis; Cepstrum; Mel frequency cepstral coefficient; Microphones; NIST; Polynomials; Speaker recognition; Support vector machines; Telephony; prosody; speaker recognition; speech recognition;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on
Conference_Location :
Taipei
ISSN :
1520-6149
Print_ISBN :
978-1-4244-2353-8
Electronic_ISBN :
1520-6149
Type :
conf
DOI :
10.1109/ICASSP.2009.4960556
Filename :
4960556
Link To Document :
بازگشت