Sevi: Speech-to-Visualization through Neural Machine Translation.
Jiawei TangYuyu LuoMourad OuzzaniGuoliang LiHongyang ChenPublished in: SIGMOD Conference (2022)
Keyphrases
- machine translation
- finite state transducers
- language independent
- information extraction
- speech recognition
- cross language information retrieval
- language processing
- natural language processing
- cross lingual
- chinese english
- natural language generation
- target language
- word sense disambiguation
- language resources
- speech signal
- natural language
- statistical machine translation
- brazilian portuguese
- automatic speech recognition
- machine translation system
- broadcast news
- word level
- artificial intelligence
- tasks in natural language processing
- parallel corpora
- language modeling
- co occurrence
- probabilistic model
- search engine