Novel Speech Motion Generation by Modeling Dynamics of Human Speech Production.
Kurima SakaiTakashi MinatoCarlos Toshinori IshiHiroshi IshiguroPublished in: Frontiers Robotics AI (2017)
Keyphrases
- speech recognition
- language acquisition
- human communication
- recognition engine
- speech signal
- automatic speech recognition
- audio visual
- speech synthesis
- spoken language
- text to speech
- human movements
- camera motion
- computer vision
- space time
- hidden markov models
- optical flow
- human arm
- dynamical models
- hearing impaired
- emotional state
- body movements
- speaker identification
- static images
- dynamic model
- key frames
- motion model
- image sequences