Unsupervised N-Best based model adaptation using model-level confidence measures

7th International Conference on Spoken Language Processing, ICSLP 2002

Volumn , Issue , 2002, Pages 69-72

  Kwan, Ka Yan ^a   Lee, Tan ^a   Yang, Chen ^a  

^a CHINESE UNIVERSITY OF HONG KONG   (Hong Kong)

Author keywords

[No Author keywords available]

Indexed keywords

HIDDEN MARKOV MODELS; MARKOV PROCESSES; MAXIMUM LIKELIHOOD;

CONFIDENCE MEASURE; MAXIMUM LIKELIHOOD LINEAR REGRESSION; MODEL ADAPTATION; N-BEST HYPOTHESIS; SCREENING DATA; UNSUPERVISED ADAPTATION; WORD ERROR RATE;

SPEECH RECOGNITION;

EID: 20244380199     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (10)

1. C. H. Lee, C. H. Lin, B. H. Juang, "A study on speaker adaptation of the parameters of continuous density hidden Markov models", IEEE trans Signal Processing, vol. 39, pp. 806-814, 1991.
2. C. J. Legetter, P. C. Woodland, "Maximum Likelihood Linear Regression for Speaker Adaptation of Continuous Density HMMs", Computer Speech and Language, Vol. 9, pp. 697-708, 1995.
3. P. Nguyen, P. Gelin, J-C. Hunqua, J-T Chien, "N-best Based Supervised and Unsupervised adaptation for Native and Non-native speakers in Cars", IEEE Proceedings, vol 1, 1999.
4. F. Wallhoff, D Willett, G. Rigoll, "Frame-Discriminative and Confidence-Driven Adaptation for LVSCR", ICASSP'00, pp. 1835-1838, 2000.
5. F. Wessel, R. Schluter, K. Macherey, H. Ney, "Confidence Measures fro Large Vocabulary Continuous Speech Recognition", IEEE Transactions on Speech and Audio Processing, Volume: 9 Issue: 3, 2001.
6. M. Weintraub, "LVCSR Log-Likelihood Ratio Scoring for Keyword Spotting", ICASSP'95, Detroit, pp. 297-300, 1995.
7. M. Liu, B. Xu, T. Hunng, Y. Deng, C. Li, "Mandarin accent adaptation based on context-independent/contentdependent pronunciation modeling", ICASSP'00, pp. 1025-1028, 2000.
8. Y. W. Wong, "Large Vocabulary Continuous Speech Recognition for Cantonese", Masters thesis, The Chinese University of Hong Kong, 2000.
9. W. N. Choi, "An Efficient Decoding Method for Continuous Speech Recognition Based on a Tree-Structured Lexicon", Masters thesis, The Chinese University of Hong Kong, 2001.
10. "http://dsp. ee.cuhk.edu.hk/speech/cucall"