Title :
Solutions for robust speech/non-speech detection in wireless environment
Author :
Karray, Lamia ; Mokbel, Chafic ; Monné, Jean
Author_Institution :
CNET, Lannion, France
Abstract :
The use of speech recognition systems in noisy environments requires robustness to adverse conditions. An efficient detection of speech/non-speech segments is therefore necessary. Several approaches have been proposed in order to improve the robustness of speech/non-speech detection used for speech recognition in noisy conditions. In this paper, we describe a robust speech/non-speech detection algorithm based on the estimation of noise statistics: mean and variance. Results of several experiments carried out on a database collected over the GSM network show that this new approach improves the recognizer´s global performances, especially in very noisy environments. Then, spectral subtraction is used as a preprocessing technique aiming to increase the robustness to noisy conditions. We show that the improvements concern mainly noisy conditions such as calls from outside or from running cars
Keywords :
acoustic noise; cellular radio; spectral analysis; speech recognition; statistical analysis; GSM network; adverse conditions; mean; noise statistics; noisy environments; preprocessing technique; robust speech/nonspeech detection; robustness; running cars; spectral subtraction; speech recognition systems; variance; wireless environment; Databases; Detection algorithms; GSM; Noise reduction; Noise robustness; Signal to noise ratio; Speech enhancement; Speech recognition; Statistics; Working environment noise;
Conference_Titel :
Interactive Voice Technology for Telecommunications Applications, 1998. IVTTA '98. Proceedings. 1998 IEEE 4th Workshop
Conference_Location :
Torino
Print_ISBN :
0-7803-5028-6
DOI :
10.1109/IVTTA.1998.727714