Tandem connectionist feature extraction for conventional HMM systems

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 3, Issue , 2000, Pages 1635-1638

  Hermansky, Hynek ^a,b   Ellis, Daniel P W ^b   Sharma, Sangita ^a  

^a OREGON HEALTH AND SCIENCE UNIVERSITY   (United States)

^b INTERNATIONAL COMPUTER SCIENCE INSTITUTE   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

FEATURE EXTRACTION; GAUSSIAN DISTRIBUTION; HIDDEN MARKOV MODELS; MARKOV PROCESSES; PROBABILITY DISTRIBUTIONS; SIGNAL PROCESSING; SPEECH PROCESSING; TRELLIS CODES; ALGORITHMS; MATHEMATICAL MODELS; NEURAL NETWORKS; VECTORS;

ACOUSTIC FEATURE VECTORS; DISCRIMINATIVE FEATURES; GAUSSIAN MIXTURE DISTRIBUTION MODEL; GAUSSIAN MIXTURE MODEL; RELATIVE ERROR RATES; SPEECH RECOGNITION SYSTEMS; TANDEM CONNECTIONIST; TRAINED NEURAL NETWORKS;

SPEECH RECOGNITION;

GAUSSIAN MIXTURE MODELS; HIDDEN MARKOV MODEL; TANDEM CONNECTIONIST FEATURE EXTRACTION; WORD RECOGNITION;

EID: 0033709098     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2000.862024     Document Type: Conference Paper

References (13)

1. H. Bourlard and N. Morgan, Connectionist Speech Recognition: A Hybrid Approach. Kluwer Academic Publishers, Boston, 1994.
2. S. Young, J. Odell, D. Ollason, V. Valtchev and P. Woodland, "Hidden Markov Model Toolkit V2.1 reference manual", Technical report, Speech group, Cambridge University Engineering Department, March 1997.
3. D. Pearce, Aurora Project: Experimental framework for the performance evaluation of distributed speech recognition front-ends, ETSI working paper, September 1998.
4. B. Kingsbury and N. Morgan, "Recognizing reverberant speech with RASTA-PLP" Proc. ICASSP-97, Munich, 2:1259-1262, April 1997.
5. A. Janin, D. Ellis and N. Morgan, "Multi-stream speech recognition: Ready for prime time?" Proc. Eurospeech-99, Budapest, September 1999.
6. H. Hermansky, "Perceptual linear predictive (plp) analysis for speech", The Journal of The Acoustical Society of America, 87:1738-1752, April 1990.
7. B. Kingsbury, Perceptually-inspired Signal Processing Strategies for Robust Speech Recognition in Reverberant Environments, Ph. D. dissertation, Dept. of EECS, University of California, Berkeley, 1998.
8. S. Sharma, D. Ellis, S. Kajarekar, P. Jain and H. Hermansky, "Feature extraction using non-linear transformation for robust speech recognition on the Aurora database", in preparation.
9. H. Hermansky, S. Sharma and P. Jain, "Data-derived nonlinear mapping for feature extraction in HMM", Proc. ASRU-99, Keystone, December 1999.
10. Y. R. Bengio, R. De Mori, G. Flammia and R. Kompe, "Global optimization of a neural-hidden markov model hybrid", IEEE Trans. on Neural Networks, 3:252-258, 1992.
11. G. Rigoll and D. Willett, "A NN/HMM hybrid for continuous speech recognition with a discriminant nonlinear feature extraction", Proc. ICASSP-98, Seattle, April 1998.
12. V. Fontaine, C. Ris and J. M. Boite, "Nonlinear Discriminant Analysis for improved speech recognition", Proc. Eurospeech-97, Rhodes, 4:2071-2074, 1997.
13. G. Williams and D. Ellis, "Speech/music discrimination based on posterior probability features", Proc. Eurospeech-99, Budapest, September 1999.