Discriminative auditory features for robust speech recognition

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

Volumn 1, Issue , 2002, Pages

  Mak, Brian ^a   Tam, Yik Cheung ^a   Li, Qi ^a  

^a HONG KONG UNIVERSITY OF SCIENCE AND TECHNOLOGY   (Hong Kong)

Author keywords

[No Author keywords available]

Indexed keywords

AUDITORY FILTERS; GAUSSIAN FILTERS;

COMPUTATIONAL COMPLEXITY; DATABASE SYSTEMS; FEATURE EXTRACTION; MARKOV PROCESSES; MATHEMATICAL MODELS; OPTIMIZATION; SIGNAL FILTERING AND PREDICTION;

SPEECH RECOGNITION;

EID: 0036299194     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (10)

1. An auditory system-based feature for robust speech recognition
2. Discriminative training for minimum error classification
3. Discriminant-function-based minimum recognition error rate pattern-recognition approach to speech recognition
4. An alphanet approach to optimising input transformations for continuous speech recognition
5. HMM-based speech recognition using state-dependent, discriminatively derived transforms on mel-warped DFT features
6. Simultaneous ANN feature and HMM recognizer design using string-based minimum classification error (MCE) training
7. An application of discriminative feature extraction to filter-bank-based speech recognition
8. The AURORA experimental framework for the performance evaluations of speech recognition systems under noisy conditions
9. A database for speaker-independent digit recognition
10. Minimum error rate training of inter-word context context-dependent acoustic model units in speech recognition