Title :
Sigmoidal spectral conversion with changeable dynamic region for speech feature extraction
Author :
Oh, Kwang Cheol ; Lee, Hwang Soo
Author_Institution :
Dept. of Electr. Eng., Korea Adv. Inst. of Sci. & Technol., Seoul, South Korea
fDate :
1/21/1999 12:00:00 AM
Abstract :
A noise-resistant feature extraction method for speech recognition in adverse conditions is presented. The proposed method converts the speech spectrum by adjusting the dynamic region of the spectrum based on the level dependent property of auditory nerves. With this method, it is possible to alleviate the problems caused by shrunken spectral dynamic region from heavy background noise
Keywords :
feature extraction; interference suppression; noise; speech recognition; adverse conditions; auditory nerves; changeable dynamic region; heavy background noise; level dependent property; noise-resistant feature extraction method; sigmoidal spectral conversion; speech feature extraction; speech recognition; speech spectrum conversion;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19990120
