Comparison of Speech Activity Detection Techniques for Speaker Recognition
This work addresses the problem of improving speaker recognition accuracy by comparing SAD techniques, but it is incremental as it reviews and evaluates existing methods.
The paper systematically reviewed popular speech activity detection (SAD) techniques for speaker recognition, finding that two Gaussian modeling-based SAD performed better than others in clean and noisy conditions on NIST speech corpora using a GMM-UBM classifier.
Speech activity detection (SAD) is an essential component for a variety of speech processing applications. It has been observed that performances of various speech based tasks are very much dependent on the efficiency of the SAD. In this paper, we have systematically reviewed some popular SAD techniques and their applications in speaker recognition. Speaker verification system using different SAD technique are experimentally evaluated on NIST speech corpora using Gaussian mixture model- universal background model (GMM-UBM) based classifier for clean and noisy conditions. It has been found that two Gaussian modeling based SAD is comparatively better than other SAD techniques for different types of noises.