Voice activity detection using periodioc/aperiodic coherence features

  • Sofia Ben Jebara
  • Published 2008 in 2008 16th European Signal Processing Conference

Abstract

This paper introduces novel features for Voice Activity Detection (VAD). They are based on the coherence function between the considered frame and its LPC residue, calculated for both periodic and aperiodic components. The development of these features was motivated by the possible distinction between the periodicity and the aperiodicity character of speech… (More)

Topics

8 Figures and Tables

Cite this paper

@article{Jebara2008VoiceAD, title={Voice activity detection using periodioc/aperiodic coherence features}, author={Sofia Ben Jebara}, journal={2008 16th European Signal Processing Conference}, year={2008}, pages={1-5} }