Effective extraction of acoustic features after noise reduction for speech classification

Author

Hurtado, J.E. ; Castellanos, G. ; Suarez, J.F.

fYear

2002

fDate

2002

Firstpage

245

Lastpage

248

Abstract

A methodology, which is oriented to voice classification, is proposed for selecting acoustic features. The raw voice characteristic assemble is preprocessed by means of statistical techniques and thereafter its reduction up to the lowest assemble dimension of representative voice parameters is accomplished, yet preserving enough discriminating properties of voice classes. The methodology introduced shows an important reduction in initial assemble dimension of voice characteristics. In addition, a method of background noise reduction for quality improvement of acoustic voice analysis is developed. The method accomplishes a spectral subtraction technique.

Keywords

acoustic signal processing; feature extraction; signal classification; spectral analysis; speech enhancement; speech recognition; statistical analysis; acoustic feature extraction; acoustic voice analysis; automatic speech recognition; background noise reduction; discriminating properties; preprocessing; quality improvement; raw voice characteristic assemble; spectral subtraction; speech classification; statistical techniques; voice classes; voice classification; Acoustic measurements; Assembly; Automatic speech recognition; Background noise; Feature extraction; Noise measurement; Noise reduction; Signal analysis; Speech analysis; Speech enhancement;

fLanguage

English

Publisher

ieee

Conference_Titel

Modern Problems of Radio Engineering, Telecommunications and Computer Science, 2002. Proceedings of the International Conference

Print_ISBN

966-553-234-0

Type

conf

DOI

10.1109/TCSET.2002.1015947

Filename

1015947