Title :
Voice activity detector employing generalised Gaussian distribution
Author :
Chang, J.-H. ; Shin, J.W. ; Kim, N.S.
Author_Institution :
Dept. of Electr. & Comput. Eng., Univ. of California, Santa Barbara, CA, USA
Abstract :
A novel approach to a voice activity detector (VAD) in noisy environments is presented. The generalised Gaussian distribution (GGD) is employed as a parametric model for noisy speech, which enables tuning to the actual data. According to the experimental results, it was discovered that the proposed GGD model is more effective for the VAD algorithm compared to the conventional Laplacian model.
Keywords :
Gaussian distribution; signal detection; speech coding; Laplacian model; generalised Gaussian distribution; noisy environments; speech coding; voice activity detector;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:20047090
