Satya Dharanipragada, Salim Roukos
IEEE Transactions on Speech and Audio Processing
This paper 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%.
Satya Dharanipragada, Salim Roukos
IEEE Transactions on Speech and Audio Processing
Mahesh Viswanathan, Homayoon S.M. Beigi, et al.
IJDAR
George Saon, Satya Dharanipragada, et al.
ICASSP 2004
Satya Dharanipragada
ISCAS 2002