Title :
Voice activity detection in nonstationary noise
Author :
Tanyer, Suleyman Gokhun ; Ozer, H.
Author_Institution :
Dept. of Electr. & Electron. Eng., Baskent Univ., Ankara
fDate :
7/1/2000 12:00:00 AM
Abstract :
A new fusion method for voice activity detection in additive nonstationary noise is suggested. A performance study of the methods: fusion, the geometrically adaptive energy level, periodicity measure, and zero crossings rates, is presented. The new method is shown to operate reliably down to -5 dB SNR
Keywords :
acoustic noise; speech processing; fusion method; geometrically adaptive energy level; nonstationary noise; performance; periodicity measure; voice activity detection; zero crossings rates; Additive noise; Energy measurement; Energy states; Noise level; Noise measurement; Probability distribution; Signal to noise ratio; Speech analysis; Speech enhancement; Telephony;
Journal_Title :
Speech and Audio Processing, IEEE Transactions on
