Incremental on-line feature space MLLR adaptation for telephony speech recognition

7th International Conference on Spoken Language Processing, ICSLP 2002

Volumn , Issue , 2002, Pages 1417-1420

  Li, Yongxin ^a   Erdogan, Hakan ^a   Gao, Yuqing ^a   Marcheret, Etienne ^a  

^a IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

MAXIMUM LIKELIHOOD;

ACOUSTICAL MODEL; FEATURE SPACE; LINE FEATURES; MAXIMUM LIKELIHOOD LINEAR REGRESSION; ON-LINE ADAPTATION; REAL TIME; TELEPHONY SPEECH RECOGNITION;

SPEECH RECOGNITION;

EID: 84969845150     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. M. J. F. Gales, "Maximum Likelihood Linear Transformations for HMM-Based Speech Recognition", Technical Report, Cambridge University Engineering Department, May 97.
2. Y. Gao, Y. Li and M. Picheny, "Maximum Rank Likelihood as an Objective function for Speech Recognition", ICSLP 2000.
3. W. Byrne and A. Gunawardana, "Discounted Likelihood Linear Regression for rapid adaptation", EUROSPEECH 1999.
4. J. Huang and M. Padmanabhan, "Fast Adaptation of Band-Quantized Speech Decoding System", submitted to Special Issue on Speech Technologies for Mobile and Portable Devices, IEEE Trans. on Speech and Audio Processing.
5. C. J. Legetter and P. C. Woodland, "Maximal Likelihood Linear Regression for Speaker Adaptation of Continuous density HMM's", Computer Speech and Language, vol. 9, no. 2, 171-186.
6. B. Maison and R. Gopinath, "Robust Confidence Annotation and Rejection for Continuous Speech Recognition", SPEECH L4, ICASSP 2001.
7. G. Saon, G. Zweig and M. Padmanabhan, "Linear Feature Space Projections for Speaker Adaptation", ICASSP 2001.