A NEW APPROACH FOR ROBUST REALTIME VOICE ACTIVITY DETECTION USING SPECTRAL PATTERN
Conference Paper
Overview
Research
Identity
Additional Document Info
Other
View All
Overview
abstract
In this paper a Voice Activity Detection approach is proposed which applies a voting algorithm to decide on the existence of speech in audio signal. For this purpose, the proposed approach uses three different short time features along with the pattern of spectral peaks of every frame. Spectral peaks pattern is appropriate for determining vowel sounds in speech signal even in the presence of noise. Therefore this measure can be applicable in voice activity detection in which the vowels characterize the speech signal. Experiments show that incorporating this measure along with our recently proposed approach for VAD, will improve the results of the algorithm considerably while imposing little computational overhead. The proposed approach is evaluated on different datasets with various noises and SNR levels and satisfying results are achieved. 2010 IEEE.
name of conference
2010 IEEE International Conference on Acoustics, Speech and Signal Processing