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