DSE-TTS: Dual Speaker Embedding for Cross-Lingual Text-to-Speech.
Sen LiuYiwei GuoChenpeng DuXie ChenKai YuPublished in: INTERSPEECH (2023)
Keyphrases
- text to speech
- cross lingual
- prosodic features
- speech synthesis
- machine translation
- language modeling
- cross lingual information retrieval
- language independent
- cross language
- event extraction
- word processing
- vector space
- text classification
- translation model
- parallel corpora
- transfer learning
- parallel corpus
- artificial intelligence
- natural language
- probabilistic model
- natural language processing
- query translation
- language model
- cross language information retrieval
- audio visual
- data mining
- speech recognition
- document clustering