Robust feature selection using probabilistic union models

6th International Conference on Spoken Language Processing, ICSLP 2000

Volumn , Issue , 2000, Pages

  Ming, Ji ^a   Jancovic, Peter ^a   Hanna, Philip ^a   Stewart, Darryl ^a   Jack Smith, F ^a  

^a QUEEN'S UNIVERSITY BELFAST   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

ADDITIVE NOISE; CRIME; FREQUENCY BANDS;

ISOLATED WORD RECOGNITION; NOISE CHARACTERISTIC; ROBUST FEATURE SELECTION; ROBUST SPEECH RECOGNITION; SPEAKER INDEPENDENTS; SPEECH UTTERANCE; STATISTICAL APPROACH; STATISTICAL DISTRIBUTION;

SPEECH RECOGNITION;

EID: 85009110213     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. Ming, J., and Smith, F. J. "Union: a new approach for combining sub-band observations for noisy speech recognition", Robust'99, pp. 175-178.
2. Ming, J., Stewart, D., Hanna, P. and Smith, F. J. "A probabilistic union model for partial and temporal corruption of speech", IEEE Workshop on ASRU, pp. 43-46, 1999.
3. Ming, J., and Smith, F. J. "A probabilistic union model for sub-band based robust speech recognition", ICASSP'2000, pp. 1787-1790.
4. Ming, J., Hanna, P., Stewart, D., Jancovic, P., and Smith, F. J. "Union: a model for speech recognition subjected to partial and temporal corruption with unknown, time-varying noise statistics", to be presented in EUSIPCO'2000.
5. Ming, J., and Smith, F. J. "Union: a new approach for combining sub-band observations for noisy speech recognition", Speech Communication, to appear.
6. Bourlard, H. "Non-stationary multi-channel (multi-stream) processing towards robust and adaptive ASR", Robust'99, pp. 1-10.
7. Hermansky, H., Tibrewala, S. and Pavel. M., "Towards ASR on partially corrupted speech". ICSLP'96, pp. 462-465.