Cross-lingual Text-To-Speech with Flow-based Voice Conversion for Improved Pronunciation.
Nikolaos EllinasGeorgios VamvoukakisKonstantinos MarkopoulosGeorgia ManiatiPanos KakoulidisJune Sig SungInchul HwangSpyros RaptisAimilios ChalamandarisPirros TsiakoulisPublished in: CoRR (2022)
Keyphrases
- text to speech
- cross lingual
- speech synthesis
- prosodic features
- language independent
- machine translation
- language modeling
- cross lingual information retrieval
- event extraction
- cross language
- word processing
- speech recognition
- spontaneous speech
- news articles
- parallel corpus
- document clustering
- text classification
- text to speech synthesis
- translation model
- parallel corpora
- transfer learning
- human machine interaction
- information extraction
- text categorization
- mono lingual
- natural language processing