Voice Activity Detection Using Generalized Exponential Kernels for Time and Frequency Domains.

In this paper, we present a simple and robust voice activity detection algorithm using a generalized exponential kernel (GEVAD). Taking advantage of a non-linear metrics, kernel functions are used to classify acoustic signatures as speech and non-speech. The analysis are performed for different signal features in the frequency domain, based on elements of the short-time discrete Fourier transform as well as in time domain, namely the short time energy. The performance of all the features was compared to each other and the best was assessed by the GEVAD algorithm. Also, insights of how to choose the best kernel function are given based in frame error rate analysis. To test the efficiency of our approaches, comparisons with other existing algorithms are presented, with GEVAD showing better performance in adverse environments as stationary (and non-stationary) low signal-to-noise ratio. [ABSTRACT FROM AUTHOR]