Voice activity detection using a periodicity measure

Abstract
The paper describes a voice activity detector (VAD) that can operate reliably in SNRs down to 0 dB and detect most speech at −5 dB. The detector applies a least-squares periodicity estimator to the input signal, and triggers when a significant amount of periodicity is found. It does not aim to find the exact talkspurt boundaries and, consequently, is most suited to speech-logging applications where it is easy to include a small margin to allow for any missed speech. The paper discusses the problem of false triggering on nonspeech periodic signals and shows how robustness to these signals can be achieved with suitable preprocessing and postprocessing.

This publication has 0 references indexed in Scilit: