Meta Talk: Learning To Data-Efficiently Generate Audio-Driven Lip-Synchronized Talking Face With High Definition.
Yuhan ZhangWeihua HeMinglei LiKun TianZiyang ZhangJie ChengYaoyuan WangJianxing LiaoPublished in: ICASSP (2022)
Keyphrases
- database
- data sets
- prior knowledge
- high quality
- data collection
- data analysis
- high definition
- learning algorithm
- multimedia
- training data
- learning process
- data quality
- background knowledge
- supervised learning
- active learning
- real time
- xml documents
- data mining techniques
- signal processing
- image quality
- data structure
- reinforcement learning
- computer vision