Voice activity detection using periodioc/aperiodic coherence features
Sofia Ben Jebara · 2008
This paper introduces novel features for Voice Activity De-tection (VAD). They are based on the coherence function be-tween the considered frame and its LPC residue, calculated for both periodic and aperiodic components. The develop-ment of these features was motivated by the possible distinc-tion between the periodicity and the aperiodicity character of speech and noise frames. Two statistical based decision techniques are used, they are the Discriminant Analysis (DA) and Gaussian Mixture Models (GMM) based bayesian clas-sifier. We tested the proposed VAD technique on TIMIT database. We obtain consistent improvement as compared to features without periodic and aperiodic decomposition. In addition, we obtain encouraging results in real environmen-tal noise.