Speaker selection training for large vocabulary continuous speech recognition

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 1, Issue , 2002, Pages 609-612

  Huang, Chao ^a   Chen, Tao ^b   Chang, Eric ^a  

^a MICROSOFT RESEARCH ASIA   (China)

^b TSINGHUA UNIVERSITY   (China)

Author keywords

[No Author keywords available]

Indexed keywords

HIDDEN MARKOV MODEL; SPEAKER DEPENDENT MODEL; SPEAKER RECOGNITION; SPEAKER SELECTION TRAINING;

COMPUTATIONAL COMPLEXITY; MARKOV PROCESSES; MATHEMATICAL MODELS; MATHEMATICAL TRANSFORMATIONS; MAXIMUM LIKELIHOOD ESTIMATION; PARAMETER ESTIMATION; PRINCIPAL COMPONENT ANALYSIS; SPEECH SYNTHESIS;

CONTINUOUS SPEECH RECOGNITION;

EID: 0036296964     PISSN: 15206149     EISSN: None     Source Type: Journal    
DOI: 10.1109/ICASSP.2002.5743791     Document Type: Article

References (10)

1. Maximum likelihood linear regression for speaker adaptation of continuous density hidden markov models
2. Analysis of speaker variability
3. Cohorts based custom models for rapid speaker and dialect adaptation
4. Speaker clustering and transformation for speaker adaptation in speech recognition systems
5. Speaker adaptation based on pre-clustering training speakers
6. A posteriori and a priori transformations for speaker adaptation in large vocabulary speech recognition systems
7. Unsupervised speaker adaptation based on sufficient HMM statistics of selected speakers
8. Large vocabulary Mandarin speech recognition with different approaches in modeling tones
9. A comparison of novel techniques for rapid speaker adaptation