Visualtts: TTS with Accurate Lip-Speech Synchronization for Automatic Voice Over.
Junchen LuBerrak SismanRui LiuMingyang ZhangHaizhou LiPublished in: ICASSP (2022)
Keyphrases
- text to speech
- speech synthesis
- prosodic features
- multimodal interaction
- text to speech synthesis
- visual speech recognition
- fully automatic
- word processing
- multi stream
- high accuracy
- visual speech
- high precision
- semi automatic
- audio visual speech recognition
- high quality
- emotion recognition
- vocal tract
- data sets
- real time