The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON COMMUNICATIONS
Transactions ID Number: 32-759
Full Name: Kun-Ching Wang
Position: Assistant Professor
Age: ON
Sex: Male
Address: No. 200, University Rd, Neimen Shiang, Kaohsiung, Taiwan, 845, R.O.C
Country: TAIWAN
Tel:
Tel prefix:
Fax:
E-mail address: wkc0224@seed.net.tw
Other E-mails:
Title of the Paper: A Method Using a Combination of Sub-Band Auto-Correlation Function for Detecting Voice-Activity
Authors as they appear in the Paper:
Email addresses of all the authors:
Number of paper pages: 11
Abstract: A novel voice activity detection (VAD) algorithm using auto-correlation function with sub-band weighting in the feature combination is proposed. To exploit the inherent characteristic of periodicity of speech signal, in this letter the well-known "Auto-Correlation Function (ACF)" is defined in the wavelet packet domain to evaluate the periodic intensity of each sub-band, which instead of periodic intensity of full-band system. Due to that the noise corruption on each sub-band is different from each other, the multiple features recombination is utilized in the proposed VAD system. In this letter, the signal to noise ratio (SNR) is employed to weight utility rate of each frequency sub-band. Experimental results show that the combined feature parameter can extract the speech activity under poor SNR conditions, and it is also insensitive to variable-level of noise.
Keywords: voice activity detection; auto-correlation; wavelet packet transform; sub-band weighting
EXTENSION of the file: .pdf
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress:
IP ADDRESS: 59.127.138.112
