ASRRL-TTS: Agile Speaker Representation Reinforcement Learning for Text-to-Speech Speaker Adaptation.
Ruibo FuXin QiZhengqi WenJianhua TaoTao WangChunyu QiangZhiyong WangYi LuXiaopeng WangShuchen ShiYukun LiuXuefei LiuShuai ZhangPublished in: CoRR (2024)
Keyphrases
- text to speech
- prosodic features
- speech synthesis
- speaker adaptation
- vocal tract
- reinforcement learning
- speech recognition
- text to speech synthesis
- speaker dependent
- programming tool
- word processing
- maximum likelihood
- hidden markov models
- speaker verification
- computer vision
- automatic speech recognition
- software development
- natural language processing