Utilizing visual cues in robot audition for sound source discrimination in speech-based human-robot communication.
Randy GomezLevko IvanchukKeisuke NakamuraTakeshi MizumotoKazuhiro NakadaiPublished in: IROS (2015)
Keyphrases
- visual cues
- human robot
- sound source
- dialogue system
- speech signal
- audio visual
- visual information
- human robot interaction
- low level
- speech recognition
- humanoid robot
- human users
- action selection
- multi modal
- key frames
- robotic systems
- visual data
- hidden markov models
- image sequences
- real time
- augmented reality
- video data
- face recognition
- computer vision