An Analysis of Visual Speech Information Applied to Voice Activity Detection
Authors:
- D. SodoyerDSD. Sodoyer
- C. JuttenCJC. Jutten
- 2 August 2006
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (15206149)
Abstract
We present a new approach to the voice activity detection (VAD) problem for speech signals embedded in non-stationary noise. The method is based on automatic lipreading: the objective is to detect voice activity or non-activity by exploiting the coherence between the speech acoustic signal and the speaker's lip movements. From a comprehensive analysis of lip shape parameters during speech and non-speech events, we show that a single appropriate visual parameter, defined to characterize the lip movements, can be used for the detection of sections of voice activity or more precisely, for the detection of silence sections. Detection scores obtained on spontaneous speech confirm the efficiency of the visual voice activity detector (VVAD)Keywords
This publication has 7 references indexed in Scilit:
- Solving The Inderterminations Of Blind Source Separation Of Convolutive Speech Mixtures2006
- Developing an audio-visual speech source separation algorithmSpeech Communication, 2004
- Recent advances in the automatic recognition of audiovisual speechProceedings of the IEEE, 2003
- Audio-visual enhancement of speech in noiseThe Journal of the Acoustical Society of America, 2001
- A statistical model-based voice activity detectionIEEE Signal Processing Letters, 1999
- Quantitative association of vocal-tract and facial behaviorSpeech Communication, 1998
- Study of a voice activity detector and its influence on a noise reduction systemSpeech Communication, 1995