Language-independent constrained cepstral features for speaker recognition

Constrained cepstral systems, which select frames to match various linguistic “constraints” in enrollment and test, have shown significant improvements for speaker verification performance. Past work, however, relied on word recognition, making the approach language dependent (LD). We develop languageindependent (LI) versions of constraints and compare results to parallel LD versions for English data on the NIST 2008 interview task. Results indicate that (1) LI versions show surprisingly little degradation from associated LD versions, (2) some LI constraints outperform their LD counterparts, (3) useful constraint types include phonetic, syllable position, prosodic, and speaking-rate regions, (4) benefits generally hold for different train/test lengths, and (5) constraints provide particular benefit in reducing false alarms. Overall, we conclude that constrained cepstral modeling can benefit speaker recognition without the need for languagedependent automatic speech recognition.

• Type: Journal
• Year: 2011
• Where: ICASSP
• Authors: Elizabeth Shriberg, Andreas Stolcke
• Keywords: ICASSP 2011, LD Versions, NIST 2008 Interview, Signal Processing, Speaker Verification Performance