GenerTTS: Pronunciation Disentanglement for Timbre and Style Generalization in Cross-Lingual Text-to-Speech.
Yahuan CongHaoyu ZhangHaopeng LinShichao LiuChunfeng WangYi RenXiang YinZejun MaPublished in: INTERSPEECH (2023)
Keyphrases
- cross lingual
- text to speech
- machine translation
- cross lingual information retrieval
- language modeling
- language independent
- event extraction
- cross language
- speech recognition
- text classification
- word processing
- document clustering
- news articles
- translation model
- query translation
- parallel corpus
- language model
- data mining
- parallel corpora
- english text
- information retrieval