Ultrasound-Based Silent Speech Interface using Sequential Convolutional Auto-encoder.
Kele XuYuxiang WuZhifeng GaoPublished in: ACM Multimedia (2019)
Keyphrases
- ultrasound images
- bit rate
- hands free
- speech recognition
- user interface
- rate distortion
- speech signal
- user friendly
- low complexity
- computational complexity
- text input
- recognition engine
- text to speech
- interface design
- deep learning
- speech synthesis
- motion estimation
- audio visual
- video compression
- automatic speech recognition
- dialogue system
- video codec
- spoken dialogue systems
- sparse coding
- edge detection
- neural network