TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation.
Xize ChengRongjie HuangLinjun LiTao JinZehan WangAoxiong YinMinglei LiXinyu DuanChangpeng YangZhou ZhaoPublished in: CoRR (2023)
Keyphrases
- visual speech
- text to speech
- hidden markov models
- audio visual speech recognition
- visual speech recognition
- speaker identification
- noisy environments
- audio signals
- audio signal
- acoustic features
- machine translation
- speech signal
- video signals
- broadcast news
- speech recognition
- word processing
- multi stream
- feature extraction