On speaker-independent, speaker-dependent, and speaker-adaptive speech recognition

Citations Over TimeTop 10% of 1993 papers

Abstract

The DARPA Resource Management task is used as a domain for investigating the performance of speaker-independent, speaker-dependent, and speaker-adaptive speech recognition. The error rate of the speaker-independent recognition system, SPHINX, was reduced substantially by incorporating between-word triphone models additional dynamic features, and sex-dependent, semicontinuous hidden Markov models. The error rate for speaker-independent recognition was 4.3%. On speaker-dependent data, the error rate was further reduced to 2.6-1.4% with 600-2400 training sentences for each speaker. Using speaker-independent models, the authors studied speaker-adaptive recognition. Both codebooks and output distributions were considered for adaptation. It was found that speaker-adaptive systems outperform both speaker-independent and speaker-dependent systems, suggesting that the most effective system is one that begins with speaker-independent training and continues to adapt to users.>

Related Papers

• → An HMM approach to text-prompted speaker verification(2002)21 cited
• → Speaker adaptation for large vocabulary speech recognition systems using speaker Markov models(1989)19 cited
• → On speaker-independent, speaker-dependent, and speaker-adaptive speech recognition(1991)17 cited
• → A speaker identification system with verification method based on speaker relative threshold and HMM(2003)4 cited
• → Some experiments on HMM speaker adaptation(2005)3 cited