A maximum likelihood training approach to irrelevant variability compensation based on piecewise linear transformations

INTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP

Volumn 3, Issue , 2006, Pages 1129-1132

  Huo, Qiang ^a   Zhu, Donglai ^a  

^a UNIVERSITY OF HONG KONG   (Hong Kong)

Author keywords

Feature compensation; Hidden Markov model; Maximum likelihood; Robust speech recognition

Indexed keywords

ERROR COMPENSATION; HIDDEN MARKOV MODELS; MARKOV PROCESSES; MATHEMATICAL TRANSFORMATIONS; MAXIMUM LIKELIHOOD; PIECEWISE LINEAR TECHNIQUES; SPEECH RECOGNITION; STOCHASTIC SYSTEMS;

ENVIRONMENTAL VARIABILITY; EVALUATION EXPERIMENTS; EVALUATION RESULTS; FEATURE COMPENSATION; PIECEWISE-LINEAR TRANSFORMATION; ROBUST SPEECH RECOGNITION; VARIABILITY COMPENSATION; WORD ERROR RATE REDUCTIONS;

LINEAR TRANSFORMATIONS;

EID: 34547526633     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (15)

1. Aurora document AU/217/99, "Availability of Finnish SpeechDat-Car database for ETSI STQ W1008 front-end standardisation," Nokia, Nov 1999.
2. L. Deng, A. Acero, M. Plumpe, and X.-D. Huang, "Large-vocabulary speech recognition under adverse acoustic environments," Proc. ICSLP-2000,2000, pp.III-806-809.
3. L. Deng, A. Acero, L. Jiang, J. Droppo, and X.-D. Huang, "High-performance robust speech recognition using stereo training data," Proc. ICASSP-2001, 2001, pp.I-301-304.
4. L. Deng, J. Wu, J. Droppo, and A. Acero, "Analysis and comparison of two speech feature extraction/compensation algorithms," IEEE Signal Processing Letters, Vol.12, No.6, pp.477-480, 2005.
5. J. Droppo and A. Acero, "Maximum mutual information SPLICE transform for seen and unseen conditions," Proc. Eurospeech-2005, 2005, pp.989-992.
6. J. Droppo, M. Mahajan, A. Gunawardana, and A. Acero, "How to train a discriminative front end with stochastic gradient descent and maximum mutual information," Proc. ASRU-2005, 2005, pp.41-46.
7. ETSI standard document, "Speech processing, transmission and quality aspects (STQ); distributed speech recognition; advanced front-end feature extraction algorithm; compression algorithms", ETSI ES 202 050 v1.1.1 (2002-10), 2002.
8. M. J. F. Gales, "Maximum likelihood linear transformations for HMM-based speech recognition," Computer Speech and Language, Vol. 12, pp.75-98, 1998.
9. H. G. Hirsch and D. Pearce, "The AURORA experimental framework for the performance evaluations of speech recognition systems under noisy conditions," ISCA ITRW ASR-2000, Paris, France, 2000.
10. D. Povey, B. Kingsbury, L. Mangu, G. Saon, H. Soltau, and G. Zweig, "fMPE: Discriminatively trained features for speech recognition," Proc. ICASSP-2005, 2005, pp.I-961-964.
11. K. Visweswariah and P. Olsen, "Feature adaptation using projection of Gaussian posteriors," Proc. Eurospeech-2005, 2005, pp.1785-1788.
12. J. Wu and Q. Huo, "An environment compensated minimum classification error training approach and its evaluation on Aurora2 database," Proc. ICSLP-2002, Denver, 2002, pp.I-453-456.
13. J. Wu and Q. Huo, "Several HKU approaches for robust speech recognition and their evaluation on Aurora connected digit recognition tasks," Proc. Eurospeech-2003, 2003, pp.21-24.
14. J. Wu, D. Zhu and Q. Huo, "A study of minimum classification error training for segmental switching linear Gaussian hidden Markov models," Proc. ICSLP-2004, 2004.
15. J. Wu, Q. Huo and D. Zhu, "An environment compensated maximum likelihood training approach based on stochastic vector mapping," Proc. ICASSP-2005, 2005, pp.I-429-432.