Several HKU approaches for robust speech recognition and their evaluation on aurora connected digit recognition tasks

EUROSPEECH 2003 - 8th European Conference on Speech Communication and Technology

Volumn , Issue , 2003, Pages 21-24

  Wu, Jian ^a   Huo, Qiang ^a  

^a UNIVERSITY OF HONG KONG   (Hong Kong)

Author keywords

[No Author keywords available]

Indexed keywords

DATABASE SYSTEMS; SPEECH COMMUNICATION; STOCHASTIC SYSTEMS;

COMPARATIVE STUDIES; CONNECTED DIGITS; DIGIT RECOGNITION; GAUSSIANS; HONG-KONG; ROBUST SPEECH RECOGNITION; STOCHASTIC VECTORS; TEST SETS;

SPEECH RECOGNITION;

EID: 85009181040     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (9)

1. L. Deng, A. Acero, M. Plumpe and X-D. Huang, "Largevocabulary speech recognition under adverse acoustic environments", Proc. of ICSLP-2000, China, October 2000.
2. J. Droppo, L. Deng and A. Acero, "Evaluation of SPLICE on the AURORA 2 and 3 Tasks", Proc. of ICSLP-2002, Denver, US, September 2002, pp.29-32.
3. "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), October 2002.
4. H. G. Hirsch and D. Pearce, "The AURORA experimental framework for the performance evaluations of speech recognition systems under noisy conditions", ISCA ITRW ASR2000, Paris, France, September 2000.
5. B-H. Juang, W. Chou and C-H. Lee, "Minimum classification error rate methods for speech recognition", IEEE Trans. on Speech and Audio Processing, Vol. 5, pp.257-265, 1997.
6. D. Macho, L. Mauuary and et al., "Evaluation of a noiserobust DSR front-end on Aurora database", Proc. of ICSLP- 2002, Denver, US, September 2002.
7. J. Wu and Q. Huo, "An environment compensated minimum classification error training approach and its evaluation on Aurora2 database," Proc. ICSLP-2002, 2002, pp.I-453-456.
8. J. Wu and Q. Huo, "Modelling uncertainty in stochastic vector mapping with minimum classification error training for robust speech recognition," Proc. ICASSP-2003, HK, 2003.
9. J. Wu and Q. Huo, "A switching linear Gaussian hidden Markov model and its application to nonstationary noise compensation for robust speech recognition," submitted to Eurospeech-2003, Switzerland, 2003.