We present our system for speech intent detection. In traditional desktop speech applications, the user has to explicitly indicate intent-to-speak to the computer by turning the microphone on. This is to alleviate problems associated with an open microphone in an automatic speech recognition system. In this paper, we use cues derived from user pose, proximity and visual speech activity to detect speech intent and enable automatic control of the microphone. We achieve real-time performance using pre-attentive cues to eliminate redundant computation.
A vision-based microphone switch for speech intent detection
2001-01-01
360155 byte
Conference paper
Electronic Resource
English
A Vision-Based Microphone Switch for Speech Intent Detection
British Library Conference Proceedings | 2001
|Speech estimation using body-conducted speech microphone in noisy environment
Tema Archive | 2009
|