Auditory fovea based speech separation and its application to dialog system.
Kazuhiro NakadaiHiroshi G. OkunoHiroaki KitanoPublished in: IROS (2002)
Keyphrases
- sound source
- speech signal
- audio visual
- speech recognition
- signal processing
- vision system
- eye movements
- visual information
- text to speech
- automatic speech recognition
- speech synthesis
- audio features
- automatic speech recognition systems
- spoken language
- language acquisition
- real time
- dialogue system
- endpoint detection
- recognition engine
- space variant
- optic disc
- speech processing
- english text
- text to speech synthesis
- visual speech
- non stationary
- independent component analysis
- speaker recognition
- speaker identification
- moving target
- retinal images
- cross modal