DiCLET-TTS: Diffusion Model based Cross-lingual Emotion Transfer for Text-to-Speech - A Study between English and Mandarin.
Tao LiChenxu HuJian CongXinfa ZhuJingbei LiQiao TianYuping WangLei XiePublished in: CoRR (2023)
Keyphrases
- text to speech
- cross lingual
- prosodic features
- text to speech synthesis
- speech synthesis
- machine translation
- english text
- language modeling
- word processing
- language independent
- cross lingual information retrieval
- parallel corpus
- cross language
- speech recognition
- language model
- knowledge representation
- event extraction
- text categorization
- co occurrence