XLST: Cross-lingual Self-training to Learn Multilingual Representation for Low Resource Speech Recognition.
Zi-qiang ZhangYan SongMing-Hui WuXin FangLi-Rong DaiPublished in: CoRR (2021)
Keyphrases
- cross lingual
- speech recognition
- language modeling
- language model
- cross lingual information retrieval
- machine translation
- hidden markov models
- cross language
- language independent
- speech signal
- automatic speech recognition
- parallel corpus
- pattern recognition
- text classification
- translation model
- speaker identification
- news articles
- query translation
- transfer learning
- word segmentation
- document clustering
- machine translation system
- broadcast news
- n gram
- information retrieval