VisageSynTalk: Unseen Speaker Video-to-Speech Synthesis via Speech-Visage Feature Selection.
Joanna HongMinsu KimYong Man RoPublished in: ECCV (36) (2022)
Keyphrases
- speech synthesis
- speech recognition
- prosodic features
- vocal tract
- feature selection
- text to speech
- data access
- automatic speech recognition
- video data
- speech corpus
- remote access
- speech signal
- language model
- pattern recognition
- hidden markov models
- distributed data management
- storage management
- machine learning
- speaker identification
- feature set
- feature extraction
- real time
- broadcast news
- image processing
- speaker adaptation
- speaker dependent
- speaker recognition
- response time
- neural network