Improved cross-task recognition using MMIE training

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

Volumn 1, Issue , 2002, Pages 85-88

  Cordoba R ^a,b   Woodland, P C ^a   Gales, M J F ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

^b UNIVERSIDAD POLITÉCNICA DE MADRID   (Spain)

Author keywords

[No Author keywords available]

Indexed keywords

BROADCAST NEWS; CROSS TASK RECOGNITION; EXTENDED BAUM-WELCH ALGORITHM; HIDDEN MARKOV MODELS; MAXIMUM A POSTERIORI ADAPTATION TECHNIQUE; MAXIMUM MUTUAL INFORMATION ESTIMATION; VOICEMAIL;

BROADCASTING; CONVERGENCE OF NUMERICAL METHODS; LEARNING ALGORITHMS; LEARNING SYSTEMS; MARKOV PROCESSES; MATHEMATICAL MODELS; MAXIMUM LIKELIHOOD ESTIMATION; PARAMETER ESTIMATION; PROBABILITY DENSITY FUNCTION; REGRESSION ANALYSIS; TELEPHONE SWITCHBOARDS;

SPEECH RECOGNITION;

EID: 0036291395     PISSN: 15206149     EISSN: None     Source Type: Journal    
DOI: 10.1109/ICASSP.2002.5743660     Document Type: Article

References (12)

1. Maximum mutual information estimation of hidden Markov model parameters for speech recognition
2. Mean and variance adaptation within the MLLR framework
3. Maximum a-posteriori estimation for multivariate Gaussian mixture observations of Markov chains
4. An inequality for rational functions with applications to some statistical estimation problems
5. Flexible speaker adaptation using maximum likelihood linear regression
6. Hidden Markov models, maximum mutual information estimation and the speech recognition problem
7. Transcription of new speaking styles-voicemail
8. Improved discriminative training techniques for large vocabulary continuous speech recognition
9. Interdependence of language models and discriminative training
10. MMIE training of large vocabulary speech recognition systems
11. Large scale discriminative training of hidden Markov models for speech recognition
12. The development of the HTK broadcast news transcription system: An overview