Vocoder-Based Speech Synthesis from Silent Videos.
Daniel MichelsantiOlga SlizovskaiaGloria HaroEmilia GómezZheng-Hua TanJesper JensenPublished in: INTERSPEECH (2020)
Keyphrases
- speech synthesis
- speech recognition
- text to speech
- vocal tract
- video sequences
- prosodic features
- video frames
- video content
- video analysis
- human activities
- video database
- video surveillance
- user generated
- dynamic scenes
- video clips
- key frames
- video data
- pattern recognition
- real time
- speech corpus
- video event
- video dataset
- visual analysis
- data sets