Search

XVoice : Multi-modal sensor based speech synthesis

태그
Multi-modal Learning
Speech Processing
2 more properties

Topic : Multi-modal sensor based speech synthesis

Also known as “silent speech”
Synthesizing vocal audio by capturing the muscle signals produced during silent speech
Mainly use facial electromyography (EMG) sensor
Demo audio
“he read and reread the paper fearing the worst had happened to me”

Research 1. EMG-based Speech Content Representation

Research 2. Voice Conversion

Research 3. Domain Adaptation