Speech Reconstruction from Silent Tongue and Lip Articulation by Pseudo Target Generation and Domain Adversarial Training.
Rui-Chen ZhengYang AiZhen-Hua LingPublished in: ICASSP (2023)
Keyphrases
- vocal tract
- hearing impaired
- domain independent
- supervised learning
- training set
- domain specific
- three dimensional
- speech signal
- training phase
- high resolution
- test set
- speech recognition
- computer aided
- speech synthesis
- multi agent
- automatic speech recognition
- target tracking
- image acquisition
- motion analysis
- training examples
- training samples