Continual Speaker Adaptation for Text-to-Speech Synthesis.
Hamed HematiDamian BorthPublished in: CoRR (2021)
Keyphrases
- text to speech synthesis
- speaker adaptation
- speech recognition
- maximum likelihood
- text to speech
- automatic speech recognition
- speaker dependent
- speaker independent
- speech recognizer
- speech signal
- neural network
- information extraction
- vocal tract
- language model
- broadcast news
- probabilistic model
- pattern recognition
- bayesian networks
- multimedia
- computer vision