Mixed-Phoneme BERT: Improving BERT with Mixed Phoneme and Sup-Phoneme Representations for Text to Speech.
Guangyan ZhangKaitao SongXu TanDaxin TanYuzi YanYanqing LiuGang WangWei ZhouTao QinTan LeeSheng ZhaoPublished in: INTERSPEECH (2022)
Keyphrases
- speech synthesis
- text to speech
- speech recognition
- prosodic features
- automatic speech recognition
- context dependent
- language model
- hidden markov models
- data sets
- automatic speech recognition systems
- speaker dependent
- website
- higher level
- general purpose
- speaker identification
- information systems
- search engine
- artificial intelligence
- machine learning
- phoneme recognition
- database