A Speech Enhancement Method Based on Signal Subspace and Hearing Masking Effect

Author

Chensheng, Jin ; Xueying, Zhang ; Hairong, Jia

Author_Institution

Coll. of Inf. Eng., Taiyuan Univ. of Technol., Taiyuan, China

Volume

3

fYear

2009

fDate

25-27 Dec. 2009

Firstpage

15

Lastpage

18

Abstract

A speech enhancement method based on signal subspace and hearing masking effect is proposed. This method has following steps. Firstly, by subspace filter the noisy speech is enhanced. Then by Johnston hearing masking model the noise hearing masking threshold is gained. Finally, by a perceptual filter based on hearing masking effect the enhanced speech is smoothed, the clean speech is gained. Simulation results show that under the background of white and train noise, the SNR in this method is more excellent than in the traditional subspace method, meanwhile the musical noise after the enhancement is depressed effectively.

Keywords

filtering theory; hearing; speech enhancement; white noise; SNR; hearing masking effect; musical noise; noise hearing masking threshold; noisy speech; perceptual filter; signal subspace; speech enhancement method; subspace filter; train noise; white noise; Application software; Auditory system; Background noise; Computational modeling; Computer applications; Educational institutions; Masking threshold; Speech coding; Speech enhancement; Wiener filter; hearing masking effect; perceptual filter; signal subspace; speech enhancement;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Science-Technology and Applications, 2009. IFCSTA '09. International Forum on

Conference_Location

Chongqing

Print_ISBN

978-0-7695-3930-0

Electronic_ISBN

978-1-4244-5423-5

Type

conf

DOI

10.1109/IFCSTA.2009.241

Filename

5384704