VOICE ACTIVITY DETECTION USING A CONTEXTUAL INFORMATION AND MULTIPLE HYPOTHESIS TESTING

This paper shows a revised statistical test for voice activi-ty detection in noise adverse environments. The method is based on a revised contextual likelihood ratio test (LRT) defined over a multiple observation window. The new ap-proach not only evaluates the two hypothesis consisting on all the observations to be speech or non-speech but all the possible hypothesis defined over the individual ob-servations. The implicit hangover mechanism artificial-ly added by the original method was not found in the revised method so its design can be further improved. With these and other innovations the proposed method showed a high speech/non-speech discrimination over a wide range of SNR conditions. The experimental frame-work showed that the revised method yields significant improvements over standardized VADs for discontinous voice transmission and distributed speech recognition, as well as over recently reported methods. 1