Audio-Visual Voice Activity Detection Based on an Utterance State Transition Model.
Takami YoshidaKazuhiro NakadaiPublished in: Adv. Robotics (2012)
Keyphrases
- audio visual
- voice activity detection
- state transition model
- speech recognition
- state transition
- hidden markov models
- noisy environments
- multi modal
- transition model
- appearance model
- visual information
- visual data
- multi stream
- black box
- language model
- input output
- multimedia
- pattern recognition
- automatic speech recognition
- speech signal
- markov chain
- audio visual speech recognition
- state space
- databases
- image processing
- metadata
- noise reduction