A Voice Activity Detection Algorithm for Wireless Communication Systems with Dynamically Varying Background Noise

摘要

Speech can be modeled as short bursts of vocal energy separated by silence gaps. During typical conversation, talkspurts comprise only 40% of each party's speech and remain- ing 60% is silence. Communication systems can achieve spectral gain by disconnecting the users from the spectral resource during sileflce periods. This letter develops a simple and efficient Voice Activity Detection (VAD) algorithm to work in a mobile envi- ronment exhibiting dynamically varying background noise. The VAD uses a classification method involving the full-band energy, ratio of low-band energy to full-band energy, zero-crossing rate, and peakiness measure.