Statistical estimation of unreliable features for robust speech recognition

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

Volumn 3, Issue , 2000, Pages 1731-1734

  Renevey, Philippe ^a   Drygajlo, Andrzej ^a  

^a EPFL   (Switzerland)

Author keywords

[No Author keywords available]

Indexed keywords

COVARIANCE MATRIX; DEEP NEURAL NETWORKS; GAUSSIAN DISTRIBUTION; HIDDEN MARKOV MODELS; MARKOV PROCESSES; SIGNAL PROCESSING; SPEECH; SPEECH PROCESSING; TRELLIS CODES; ACOUSTIC SIGNAL PROCESSING; FEATURE EXTRACTION; MATHEMATICAL MODELS; PROBABILITY DENSITY FUNCTION; SIGNAL DETECTION; SIGNAL TO NOISE RATIO; SPURIOUS SIGNAL NOISE; STATISTICAL METHODS;

CONTINUOUS DENSITY HIDDEN MARKOV MODELS; DETECTION AND ESTIMATION; GAUSSIAN MIXTURE MODEL; HIDDEN MARKOV MODELS (HMMS); PROBABILISTIC MEASURES; ROBUST SPEECH RECOGNITION; STATISTICAL ESTIMATION; STATISTICAL MODELING;

SPEECH RECOGNITION;

AUTOMATIC SPEECH RECOGNITION; CONTINUOUS DENSITY HIDDEN MARKOV MODEL; GAUSSIAN MIXTURE MODEL; ROBUST SPEECH RECOGNITION; STATISTICAL SPECTRAL SUBTRACTION;

EID: 0033709389     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2000.862086     Document Type: Conference Paper

References (11)

1. Cooke, M., Green, P., and Crawford, M., "Handling missing data in speech recognition", in Int. Conf. on Spoken Language Processing (ICSLP), pp. 1555-1558, 1994.
2. Lippmann, R. P. and Carlson, B. A., "Using missing feature theory to actively select features for robust speech recognition with interruptions, filtering and noise", in Eurospeech, vol. 1, pp. 37-40, Rhodes, Greece, Sep. 1997.
3. Cooke, M., Morris, A., and Green, P., "Missing data techniques for robust speech recognition", in Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), pp. 863-866, 1997.
4. Drygajlo, A. and El-Maliki, M., "Speaker verification in noisy environments with combined spectral subtraction and missing feature theory", in Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), pp. 121-124, 1998.
5. Drygajlo, A. and El-Maliki, M., "Use of the generalized spectral subtraction and missing feature compensation for robust speaker verification", in RLA2C, pp. 80-83, Avignon, 1998.
6. Vizinho, A., Green, P., Cooke, M., and Josifovski, L., "Missing data theory, spectral subtraction and signal-to-noise estimation for robust asr: an integrated study", in Eurospeech, vol. 5, pp. 2407-2410, 1999.
7. El-Maliki, M., Renevey, P., and Drygajlo, A., "Rehaussement par soustraction spectrale et compensation des parametres manquants pour la reconnaissance robuste du locuteur et de la parole", in JEP'98 (Journée d'Étude de la Parole), pp. 409-412, Martigny, 1998.
8. Renevey, P. and Drygajlo, A., "Missing feature theory and probabilistic estimation of clean speech components for robust speech recognition", in Eurospeech, vol. 6, pp. 2627-2630, 1999.
9. Drygajlo, A. and El-Maliki, M., "Spectral subtraction and missing feature modeling for speaker verification", in Proc. of EUSIPCO'98, pp. 355-358, Rhodes, September 1998.
10. Morris, A. C, Cooke, M. P., and Green, P. D., "Some solution to the missing feature problem in data classification, with application to noise robust ASR", in Int. Conf. on Acoustics. Speech and Signal Processing (ICASSP), pp. 737-740, 1998.
11. Josifovski, L., Cooke, M., Green, P., and Vizinho, A., "State based imputation of missing data for robust speech recognition and speech enhancement", in Eurospeech, vol. 6, pp. 2833-2836, 1999.