INTEGRATED OPTIMIZATION OF FEATURE TRANSFORMATION FOR SPEECH RECOGNITION

4th European Conference on Speech Communication and Technology, EUROSPEECH 1995

Volumn , Issue , 1995, Pages 109-112

  Euler, S ^a  

^a Bosch Telecom GmbH   (Germany)

Author keywords

discriminative training; feature transformation; speech recognition

Indexed keywords

LINEAR TRANSFORMATIONS; METADATA; SPEECH COMMUNICATION;

DESCENT METHOD; DISCRIMINATIVE TRAINING; FEATURE TRANSFORMATIONS; FEATURES VECTOR; FUNCTIONAL APPROXIMATION; GENERALIZED PROBABILISTIC DESCENTS; INTEGRATED OPTIMIZATION; NEW APPROACHES; OPTIMAL LINEAR TRANSFORMATION; TRANSFORMATION MATRIX;

SPEECH RECOGNITION;

EID: 33747684554     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (5)

1. F. Class, A. Kaltenmeier, and P. Regel-Brietzmann. Optimization of an HMM~based continuous speech recognizer. In EUROSPEECH 93, pages 803-806, Berlin, 1993.
2. E. G. Schukat-Talamazzini, J. Hornegger, and H. Niemann. Optimal linear feature transformations for semi-continuous hidden Markov models. In ICASSP-95, Detroit, 1995.
3. L. Deng. Integrated optimization of dynamic feature parameters for hidden Marov modehng of speech. IEEE Signal Processing Letters, SPL - 1:66-69, 1994.
4. W. Chou, B. H. Juang, and C H. Lee. Segmental GPD training of HMM based speech recognizer. In ICASSP-92, pages 1-473-476, San Francisco, 1992.
5. S. Euler and J. Zinke. Experiments on the use of the generalized probabilistic descent method in speech recognition. In ICSLP-92, pages 157-160, Banff, 1992.