Light-Weight Visualvoice: Neural Network Quantization On Audio Visual Speech Separation.
Yifei WuChenda LiYanmin QianPublished in: ICASSP Workshops (2023)
Keyphrases
- lightweight
- visual speech
- neural network
- hidden markov models
- audio visual speech recognition
- visual speech recognition
- speaker identification
- audio signals
- noisy environments
- neural network model
- audio signal
- pattern recognition
- video signals
- speech signal
- broadcast news
- text to speech
- gaussian mixture model
- speech recognition
- wireless sensor networks
- acoustic features
- multimedia
- computational complexity