FULLY ADAPTIVE SVD-BASED NOISE REMOVAL FOR ROBUST SPEECH RECOGNITION

6th European Conference on Speech Communication and Technology, EUROSPEECH 1999

Volumn , Issue , 1999, Pages 1951-1954

  Hermus, Kris ^a   Dologlou, Ioannis ^a   Wambacq, Patrick ^a   Van Compernolle, Dirk ^b  

^a UNIVERSITY OF LEUVEN   (Belgium)

^b NUANCE COMMUNICATIONS   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ADDITIVE NOISE; CONTINUOUS SPEECH RECOGNITION; SPEECH COMMUNICATION; VOCABULARY CONTROL; WHITE NOISE;

LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; NEW APPROACHES; NOISES REMOVAL; OBSERVATION MATRIX; RECOGNITION PROCESS; ROBUST SPEECH RECOGNITION; SIGNAL ENHANCEMENT; SINGULAR VALUES; SPECTRA'S; SPEECH SIGNALS;

SINGULAR VALUE DECOMPOSITION;

EID: 85068269365     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (5)

1. Y. Gong. Speech recognition in noisy environments: A survey. Speech Communication, 16(3):261-291, April 1995.
2. P. C. Hansen and S. H. Jensen. FIR filter representations of reduced-rank noise reduction. In IEEE Transactions on Signal Processing, September 1996. Accepted for Publication.
3. S. H. Jensen, P. C. Hansen, S. D. Hansen, and J. A. S0rensen. Reduction of broad-band noise in speech by truncated QSVD. IEEE Transactions on Speech and Audio Processing, 3:439-448, November 1995.
4. J. Duchateau, K. Demuynck, and D. Van Compernolle. Fast and accurate acoustic modelling with semi-continuous HMMs. Speech Communication, 24(1):5-17, April 1998.
5. T. Claes, F. Xie, and D. Van Compernolle. Spectral estimation and normalisation for robust speech recognition. In Proc. International Conference on Spoken Language Processing, volume IV, pages 1997-2000, Philadelphia, U.S.A., October 1996.