Audio-visual speech recognition
Audio visual speech recognition (AVSR) is a technique that uses image processing capabilities in lip reading to aid speech recognition systems in recognizing undeterministic phones or giving preponderance among near probability decisions.
Each system lip reading and speech recognition works separately then their results are mixed at the stage of feature fusion.
External links
IBM Research - Audio Visual Speech Technologies
- SpeechTEK - speech technology education
- Speech Technology magazine - editorial content about the speech industry
| |||||||||||||||||||||||||||||||||
| |||||||||||||||||||||||||||||||||
| |||||||||||||||||||||||||||||||||
