Exploiting acoustic feature correlations by joint neural vector quantizer design in a discrete HMM system

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

Volumn 1, Issue , 1998, Pages 5-8

  Neukirchen, C ^a   Willett, D ^a   Eickeler, S ^a   Muller, S ^a  

^a UNIVERSITY OF DUISBURG ESSEN   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTIC FEATURES; HIGHLY-CORRELATED; MAXIMUM MUTUAL INFORMATION; RESOURCE MANAGEMENT; SPEAKER INDEPENDENTS; SPEECH RECOGNIZER; TRAINING METHODS; VECTOR QUANTIZERS;

STEREOPHONIC BROADCASTING;

SIGNAL PROCESSING;

EID: 0031642356     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.1998.674353     Document Type: Conference Paper

References (6)

1. K.F. Lee, et al, "An Overview of the SPHINX Speech Recognition system", IEEE Trans. Acoust, Speech, Signal Processing. 38, No. 1, Jan. 1990, pp. 35-45.
2. N. Morgan, H. Bourlard, "Neural Networks for Statistical Recognition of Continuous Speech," Proc. IEEE, Vol. 83, No. 5, May 1995, pp. 742-770.
3. Ch. Neukirchen, G. Rigoll, "Advanced training methods and new network topologies for hybrid MMI-Connectionist/HMM speech recognition systems", Proc. IEEE-ICASSP, 1997, pp. 3257-3260.
4. M. Osterndorf, J.R. Rohlicek, "Joint quantizer design and parameter estimation for discrete Hidden Markov Models", Proc. IEEE-ICASSP, 1990, pp. 705-708.
5. G. Rigoll, Ch. Neukirchen, "A new approach to hybrid HMM/ANN speech recognition using mutual information neural networks", Advances in Neural Information Processing Systems 9, NIPS*96, Denver, 1996, pp. 772-778.
6. J. Rottland, et al, "Large Vocabulary Speech Recognition with Context dependent MMI-Connectionist/HMM Systems using the WSJ Database", Proc. Eurospeech, 1997, pp. 79-82.