Voice activity detection in presence of transients using the scattering transform

Voice activity detection in the presence of highly non-stationary noise and transient interferences is an open problem. State-of-the-art voice activity detectors which are based on statistical models usually assume that noise is slowly varying with respect to speech. This assumption does not hold for transient interferences which are short time interruptions, and the performance of these detectors significantly deteriorates. In this paper, we propose a supervised learning algorithm for voice activity detection which is designed to perform in the presence of transients. We consider a labeled training set which comprises speech, background noise and transients, and propose a continuous measure for voice activity based on the Support Vector Machine (SVM) classifier. The measure of voice activity is constructed in a features domain, where the features are based on the scattering transform, include noise estimation, and are designed to separate speech and non-speech frames. Experimental results demonstrate that the proposed algorithm outperforms state-of-the-art detectors for different types of background noises, and in particular accurately classifies frames which contain transient interferences.