Speaker recognition using syllable-based constraints for cepstral frame selection

We describe a new GMM-UBM speaker recognition system that uses standard cepstral features, but selects different frames of speech for different subsystems. Subsystems, or “constraints”, are based on syllable-level information and combined at the score level. Results on both the NIST 2006 and 2008 test data sets for the English telephone train and test condition reveal that a set of eight constraints performs extremely well, resulting in better performance than other commonly-used cepstral models. Given the still largely-unexplored world of possible constraints and combinations, it is likely that the approach can be even further improved.

• Type: Conference
• Year: 2009
• Where: ICASSP
• Authors: Tobias Bocklet, Elizabeth Shriberg
• Keywords: Commonly-used Cepstral Models, GMM-UBM Speaker Recognition, ICASSP 2009, Signal Processing, Standard Cepstral Features