Quality improvement of enhanced speech in DCT domain using modified a priori SNR

Author

Hasan, Md Kamrul ; Akter, Lutfa

Author_Institution

Dept. of Electr. & Electron. Eng., Bangladesh Univ. of Eng. & Technol., Dhaka, Bangladesh

fYear

2003

fDate

14-17 Dec. 2003

Firstpage

733

Lastpage

736

Abstract

This paper illustrates the superiority of using time-frequency varying averaging factor to estimate the a priori SNR for speech enhancement using spectral subtraction rules. An expression for the smoothing parameter is derived in the DCT domain. Improvements over conventional spectral subtraction rules in terms of objective quality measures e.g., log-area-ratio (LAR), output SNR and average segmental SNR are shown.

Keywords

discrete cosine transforms; smoothing methods; speech enhancement; time-frequency analysis; DCT domain; enhanced speech quality improvement; log-area-ratio; modified a priori SNR; smoothing parameter; spectral subtraction rules; speech enhancement; time-frequency varying averaging factor; Additive noise; Degradation; Discrete cosine transforms; Frequency estimation; Signal to noise ratio; Smoothing methods; Speaker recognition; Speech analysis; Speech enhancement; Time frequency analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing and Information Technology, 2003. ISSPIT 2003. Proceedings of the 3rd IEEE International Symposium on

Print_ISBN

0-7803-8292-7

Type

conf

DOI

10.1109/ISSPIT.2003.1341225

Filename

1341225

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=3524041