DocumentCode :
2701160
Title :
The MIT-LL/IBM 2006 Speaker Recognition System: High-Performance Reduced-Complexity Recognition
Author :
Campbell, W.M. ; Sturim, D.E. ; Shen, Wei ; Reynolds, Douglas A. ; Navratil, J.
Author_Institution :
Lincoln Lab., MIT, Lexington, MA, USA
Volume :
4
fYear :
2007
fDate :
15-20 April 2007
Abstract :
Many powerful methods for speaker recognition have been introduced in recent years - high-level features, novel classifiers, and channel compensation methods. A common arena for evaluating these methods has been the NIST speaker recognition evaluation (SRE). In the NIST SRE from 2002-2005, a popular approach was to fuse multiple systems based upon cepstral features and different linguistic tiers of high-level features. With enough enrollment data, this approach produced dramatic error rate reductions and showed conceptually that better performance was attainable. A drawback in this approach is that many high-level systems were being run independently requiring significant computational complexity and resources. In 2006, MIT Lincoln Laboratory focused on a new system architecture which emphasized reduced complexity. This system was a carefully selected mixture of high-level techniques, new classifier methods, and novel channel compensation techniques. This new system has excellent accuracy and has substantially reduced complexity. The performance and computational aspects of the system are detailed on a NIST 2006 SRE task.
Keywords :
cepstral analysis; speaker recognition; speech processing; MIT-LL/IBM 2006; cepstral features; channel compensation techniques; dramatic error rate reductions; high-performance reduced-complexity recognition; linguistic tiers; speaker recognition system; Adaptive systems; Cepstral analysis; Collision mitigation; Error analysis; Fuses; Laboratories; NIST; Speaker recognition; Speech processing; Vectors; speaker recognition; speech processing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing, 2007. ICASSP 2007. IEEE International Conference on
Conference_Location :
Honolulu, HI
ISSN :
1520-6149
Print_ISBN :
1-4244-0727-3
Type :
conf
DOI :
10.1109/ICASSP.2007.367202
Filename :
4218076
Link To Document :
بازگشت