Two-stage speaker adaptation of hybrid tied-posterior acoustic models

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

Volumn I, Issue , 2005, Pages 977-980

  Stadermann, Jan ^a   Rigoll, Gerhard ^a  

^a TECHNICAL UNIVERSITY OF MUNICH   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

ERROR ANALYSIS; MARKOV PROCESSES; MAXIMUM LIKELIHOOD ESTIMATION; NEURAL NETWORKS; SPEECH RECOGNITION;

ADAPTATION METHODS; GAUSSIAN DISTRIBUTION; GRADIENT BASED ADAPTATION STRATEGY; WORD ERROR RATE;

ACOUSTIC SIGNAL PROCESSING;

EID: 33646794050     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2005.1415279     Document Type: Conference Paper

References (9)

1. C.J. Leggetter and P.C. Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models," Computer Speech and Language, vol. 9, pp. 171-185, 1995.
2. Jean-Luc Gauvain and Chin-Hui Lee, "Maximum a-posteriori estimation for multivariate gaussian mixture observations of markov chains," IEEE Transactions on Speech and Audio Processing, vol. 2, pp. 291-298, 1994.
3. Frank Wallhoff, Daniel Willett, and Gerhard Rigoll, "Frame Discriminative and Confidence-Driven Adaptation for LVCSR," in IEEE Int. Conference on Acoustics, Speech, and Signal Processing (ICASSP), Istanbul, Turkey, June 2000, pp. 1835-1838.
4. J. Neto, L. Almeida, M. Hochberg, C. Martins, L. Nunes, S. Renals, and A. Robinson, "Speaker-Adaptation for Hybrid HMM-ANN Continuous Speech Recognition System," in Proc. EUROSPEECH, Madrid, Spain, Sept. 1995.
5. Nikko Ström, "Speaker-Adaptation by Modeling the Speaker Variation in a Continuous Speech Recognition System," in 4th Int. Conference on Spoken Language Processing (ICSLP), Philadelphia, USA, Oct. 1996.
6. J. Rottland and G. Rigoll, "Tied posteriors: An approach for effective introduction of context dependency in hybrid NN/HMM LVCSR," in Proc. ICASSP, 2000.
7. Herve Bourlard and Nelson Morgan, Connectionist Speech Recognition: A Hybrid Approach, Kluwer Academic Publishers, 1994.
8. Merten Joost and Wolfram Schiffmann, "Speeding up back-propagation algorithms by using cross-entropy combined with pattern normalization," International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems (IJUKFS), vol. 6, no. 2, pp. 117-126, 1998.
9. F. Kubala, J.R. Bellegarda, J. Cohen, D.S. Pallett, D.B. Paul, M. Phillips, R. Rajasekaran, F. Richardson, M. Riley, R. Rosenfeld, R. Roth, and M. Weintraub, "The Hub and Spoke Paradigm for CSR Evaluation," in Proc. of the ARPA Spoken Language Technology Workshop, Plainsboro, New Jersey, Mar. 1994, pp. 9-14, Morgan Kaufmann.