Title :
MVDR based feature extraction for robust speech recognition
Author :
Dharanipragada, Satya ; Rao, Bhaskar D.
Author_Institution :
Human Language Technol., IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
Abstract :
Describes a robust feature extraction method for continuous speech recognition. Central to the method is the minimum variance distortionless response (MVDR) method of spectrum estimation and a feature trajectory smoothing technique for reducing the variance in the feature vectors. The above method, when evaluated on continuous speech recognition tasks in a stationary and moving car, gave an average relative improvement in WER of greater than 30%
Keywords :
cepstral analysis; fast Fourier transforms; feature extraction; speech coding; speech recognition; statistical analysis; continuous speech recognition; feature trajectory smoothing technique; minimum variance distortionless response method; robust feature extraction method; robust speech recognition; spectrum estimation; Band pass filters; Cepstral analysis; Feature extraction; Gaussian processes; Humans; Linear predictive coding; Mel frequency cepstral coefficient; Robustness; Spectral analysis; Speech recognition;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2001. Proceedings. (ICASSP '01). 2001 IEEE International Conference on
Conference_Location :
Salt Lake City, UT
Print_ISBN :
0-7803-7041-4
DOI :
10.1109/ICASSP.2001.940829
