Keyphrases
- audio visual
- speech recognition
- audio stream
- multi stream
- speaker recognition
- real time
- automatic speech recognition
- speaker verification
- speaker identification
- particle filter
- speaker diarization
- object tracking
- data streams
- vocal tract
- acoustic features
- automatic speech recognition systems
- visual search
- speech signal
- gaussian mixture model
- particle filtering
- prosodic features
- multi modal
- speech synthesis
- visual information
- visual tracking
- kalman filter
- appearance model
- biologically plausible
- emotion recognition
- synthesized speech
- automatic transcription
- speech sounds
- speaker dependent
- hidden markov models
- speaker adaptation
- speech recognition systems
- natural images
- non stationary
- speech recognizer
- text to speech
- spoken language