Title :
Word recognition in the car-speech enhancement/spectral transformations
Author :
Mokbel, Chafic ; Chollet, Gérard
Author_Institution :
Telecom-Paris, France
Abstract :
Speech enhancement through Kalman filtering is compared to environment adaptation using spectral transformations. Important results on general characteristics of speech in noise and a possible correction to the Lombard effect are reported. It is shown that traditional speech enhancement offers little improvement to recognition. Best results are obtained with transformations applied to the reference models
Keywords :
Kalman filters; noise; speech analysis and processing; speech recognition; transforms; Kalman filtering; Lombard effect; car noise; environment adaptation; reference models; spectral transformations; speech enhancement; speech recognition; word recognition; Additive noise; Cepstral analysis; Filtering; Kalman filters; Low-frequency noise; Noise measurement; Noise robustness; Speech enhancement; Speech recognition; Working environment noise;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference on
Conference_Location :
Toronto, Ont.
Print_ISBN :
0-7803-0003-3
DOI :
10.1109/ICASSP.1991.150491
