A semi-continuous state-transition probability HMM-based voice activity detector

Authors:
H. Othman;T. Aboulnasr
Affiliations:
School of Information Technology and Engineering, Faculty of Engineering, University of Ottawa, Ontario, Canada;School of Information Technology and Engineering, Faculty of Engineering, University of Ottawa, Ontario, Canada
Venue:
EURASIP Journal on Audio, Speech, and Music Processing
Year:
2007

Citing 2
Cited 2

ITU-T Recommendation G.729 Annex B: a silence compression scheme for use with G.729 optimized for V.70 digital simultaneous voice and data applications

IEEE Communications Magazine
A robust voice activity detector for wireless communications using soft computing

IEEE Journal on Selected Areas in Communications

Energy efficient implementation of G.729 for wireless VoIP application

ICAIT '08 Proceedings of the 2008 International Conference on Advanced Infocomm Technology
Efficient voice activity detection in reverberant enclosures using far field microphones

DSP'09 Proceedings of the 16th international conference on Digital Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We introduce an efficient hidden Markov model-based voice activity detection (VAD) algorithm with time-variant state-transition probabilities in the underlying Markov chain. The transition probabilities vary in an exponential charge/discharge scheme and are softly merged with state conditional likelihood into a final VAD decision. Working in the domain of ITU-T G.729 parameters, with no additional cost for feature extraction, the proposed algorithm significantly outperforms G.729 Annex B VAD while providing a balanced tradeoff between clipping and false detection errors. The performance compares very favorably with the adaptive multi-rate VAD, option 2 (AMR2).