Voice Activity Detection based on Generalized Gamma Distribution
Jong Won Shin, Joon‐Hyuk Chang, S. Barbara, Hwan Sik Yun, Nam Soo Kim · 2006
We propose a voice activity detection (VAD) algorithm based on the generalized gamma distribution (G/spl Gamma/D). The distributions of noise spectra and noisy speech spectra, including speech-inactive intervals, are modeled by a set of G/spl Gamma/Ds and applied to the likelihood ratio test (LRT) for VAD. The parameters of G/spl Gamma/D are estimated through an on-line maximum likelihood (ML) estimation procedure where the global speech absence probability (GSAP) is incorporated under a forgetting scheme. Experimental results show that the proposed VAD algorithm, based on G/spl Gamma/D, outperformed the algorithms based on other statistical models.