TESTING FOR INDEPENDENCE AND LRT FOR VAD
J. M. Górriz, Carlos G. Puntonet, Javier Ramı́rez · International Journal of Information Acquisition · 2005
In this paper we propose a simple method for Voice Activity Detection (VAD) in noisy environments based on periodogram of squares. The approach is based on a test for independence between a sequence of identically distributed random variables using the classical technique of Likelihood Ratio Test (LRT). This algorithm differs from many others in the way the decision rule is formulated (detection tests) and the domain used in this approach. Clear improvements in the speed of speech/non-speech discrimination accuracy demonstrate the effectiveness of the proposed VAD. It has been shown that application of statistical detection test leads to a better separation of the speech and noise distributions, thus allowing a more effective discrimination and a tradeoff between complexity and performance. The experimental analysis carried out on the AURORA databases and tasks provides an extensive performance evaluation together with an exhaustive comparison to the standard VADs such as ITU G.729, GSM AMR and ETSI AFE for distributed speech recognition (DSR), and other recently reported VADs based in statistical tests.