Vocoder-Based Speech Synthesis from Silent Videos.
Daniel MichelsantiOlga SlizovskaiaGloria HaroEmilia GómezZheng-Hua TanJesper JensenPublished in: CoRR (2020)
Keyphrases
- speech synthesis
- speech recognition
- text to speech
- prosodic features
- video sequences
- vocal tract
- video frames
- speech corpus
- pattern recognition
- video data
- visual analysis
- video surveillance
- video clips
- human activities
- user generated
- image sequences
- neural network
- video database
- video analysis
- real time
- multi view
- image compression
- spatio temporal