Encoder-Decoder Architectures for Silent Speech Recognition based on High-density Surface Electromyogram.
Xi ChenXu ZhangXiang ChenXun ChenPublished in: ICARM (2022)
Keyphrases
- speech recognition
- high density
- decoding process
- video codec
- low density
- error control
- distributed video coding
- hidden markov models
- language model
- automatic speech recognition
- pattern recognition
- speech recognizer
- emg signals
- speech signal
- thin film
- rate distortion
- speech processing
- data center
- speech recognition technology
- bit rate
- speech synthesis
- noisy environments
- speaker identification
- wyner ziv
- speech recognition systems
- isolated word
- motion estimation
- independent component analysis
- video coding
- non stationary
- speaker independent
- speaker adaptation
- cost effective