The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON INFORMATION SCIENCE AND APPLICATIONS
Transactions ID Number: 32-394
Full Name: Kun-Ching Wang
Position: Assistant Professor
Age: ON
Sex: Male
Address: Department of Information Technology & Communication, Shin Chien University, No. 200, University Rd, Neimen Shiang, Kaohsiung 845
Country: TAIWAN
Tel:
Tel prefix:
Fax:
E-mail address: kunching@mail.kh.usc.edu.tw
Other E-mails: wkc0223@seed.net.tw
Title of the Paper: A Novel Wavelet Coefficient Thresholding Based on Time-Frequency Adaptation for Speech Enhancement
Authors as they appear in the Paper:
Email addresses of all the authors:
Number of paper pages: 10
Abstract: In this paper, we propose a novel wavelet coefficient threshold (WCT) based on time-frequency adaptation for providing speech enhancement robustness to non-stationary and colored noise. Different from the conventional methods in threshold choosing, e.g. invariant threshold and time-variant threshold, the proposed WCT is adapted by both time and frequency information. In order to further improve the intelligibility of the processed speech signal, we apply appropriate wavelet thresholding according to voiced/unvoiced decision. In order to suppress the appearance of musical residual noise produced by most speech enhancement systems, we consider masking properties of human auditory system to reduce the effect of musical residual noise. Simulation results showed that the proposed system is capable of reducing noise with little speech degradation and the overall performance is superior to several competitive methods in both objective and subjective evaluations.
Keywords: Speech enhancement; perceptual wavelet packet transformation; adaptive wavelet coefficient threshold; musical residual noise
EXTENSION of the file: .pdf
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress:
IP ADDRESS: 219.80.130.138
