Leveraging speaker-dependent variation of adaptation

9th European Conference on Speech Communication and Technology

Volumn , Issue , 2005, Pages 1793-1796

  Mandal, Arindam ^a   Ostendorf, Mari ^a   Stolcke, Andreas ^b  

^a University of Washington   (United States)

^b SRI INTERNATIONAL   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ADAPTIVE SYSTEMS; FEATURE EXTRACTION; PROBABILITY; REGRESSION ANALYSIS; SPEECH PROCESSING; TREES (MATHEMATICS);

LINEAR REGRESSION; MAXIMUM LIKELIHOOD; TELEPHONE SPEECH.; WORD ERROR RATE;

SPEECH RECOGNITION;

EID: 33745214663     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. C. Leggetter and P. Woodland, "Maximum likelihood linear regression for speaker adaptation of HMMs," Computer Speech and Language, vol. 9, pp. 171-186, 1995.
2. M. Gales, "The generation and use of regression class trees for MLLR adaptation," Cambridge University, Tech. Rep. CUED/F-INFENG/TR263, 1996.
3. C. Leggetter and P. Woodland, "Flexible speaker adaptation using maximum likelihood linear regression," in Proc. ARPA Spoken Language Technology Workshop, 1995, pp. 104-109.
4. C. Leggetter, "Improved acoustic modelling for HMMs using linear transformations," Ph.D. dissertation, University of Cambridge, 1995.
5. A. Stolcke and et al., "SRI system description," in EARS RT04 Workshop, Palisades, 2004.
6. L. Mangu, E. Brill, and A. Stolcke, "Finding consensus in speech recognition: Word error minimization and other applications of confusion networks," Computer Speech and Language, vol. 14, pp. 373-400, 2000.
7. L. Ubel and P. Woodland, "Improvements in linear transform based speaker adaptation," in Proc. of ICASSP, 2001.