SVTS: Scalable Video-to-Speech Synthesis.
Rodrigo MiraAlexandros HaliassosStavros PetridisBjörn W. SchullerMaja PanticPublished in: CoRR (2022)
Keyphrases
- speech synthesis
- scalable video
- end to end
- speech recognition
- bitstream
- text to speech
- video transmission over wireless
- video quality
- vocal tract
- video streaming
- joint source and channel coding
- scalable video coding
- video transmission
- bit rate
- base layer
- frame rate
- coding scheme
- computer vision
- optical flow
- feature extraction