Improved noise robustness by corrective and rival training

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

Volumn 1, Issue , 2001, Pages 293-296

  Meyer, C ^a   Rose, G ^a  

^a PHILIPS RESEARCH LABORATORIES   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

HIGH RESOLUTION ACOUSTIC MODELS; NOISE ROBUSTNESS; RIVAL TRAINING; SPEECH ENHANCEMENT; WIENER FILTERING;

ACOUSTIC NOISE; ACOUSTIC SIGNAL PROCESSING; ALGORITHMS; MATHEMATICAL MODELS; MAXIMUM LIKELIHOOD ESTIMATION;

SPEECH RECOGNITION;

EID: 0034854959     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (14)

1. Maximum mutual information estimation of hidden markov model parameters for speech recognition
2. Minimum error rate training based on N-Best string models
3. The singular value decomposition and long and short spaces of noisy matrices
4. A comparative study of linear feature transformation techniques for automatic speech recognition
5. Database and online adaptation for improved speech recognition in car environments
6. Model-based technique for noise robust speech recognition
7. Discriminative learning of additive noise and channel distortions for robust speech recognition
8. Discriminative learning for minimum error classification
9. CSDC - the MoTiV car-speech data collection
10. A combination of discriminative and maximum likelihood techniques for noise robust speech recognition
11. An improved approach to robust speech recognition using minimum error classification
12. Rival training: Efficient use of data in discriminative training
13. Comparison of discriminative training criteria
14. Large scale discriminative training for speech recognition