| Paper: | SLP-L5.4 | ||
| Session: | Advances in Speaker Recognition | ||
| Time: | Wednesday, May 17, 15:00 - 15:20 | ||
| Presentation: | Lecture | ||
| Topic: | Speech and Spoken Language Processing: Speaker Verification | ||
| Title: | Secondary Classification for GMM based Speaker Recognition | ||
| Authors: | Jason Pelecanos, Daniel Povey, Ganesh Ramaswamy, IBM T. J. Watson Research Center, United States | ||
| Abstract: | This paper discusses the use of a secondary classifier to re-weight the frame-based scores of a speaker recognition system according to which region in feature space they belong. The score mapping function is constructed to perform a likelihood ratio (LR) correction of the original LR scores. This approach has the ability to limit the effect of rogue model components and regions of feature space that may not be robust to different audio environments, handset types or speakers. Prior information available from tests on a development data set can be used to determine a log-likelihood-ratio mapping function that more appropriately weights each speech frame. The computational overhead for this approach in online mode is close to negligible for significant performance gains shown for the NIST 2004 Speaker Recognition Evaluation data. | ||
©2018 Conference Management Services, Inc. -||- email: webmaster@icassp2006.org -||- Last updated Friday, August 17, 2012