An integrated framework for transcribing Mandarin-English code-mixed lectures with improved acoustic and language modeling.
Ching-feng YehChao-Yu HuangLiang-Che SunLin-Shan LeePublished in: ISCSLP (2010)
Keyphrases
- language modeling
- cross lingual
- language model
- information retrieval
- retrieval model
- comparable corpora
- query expansion
- n gram
- probabilistic model
- speech recognition
- text classification
- natural language
- broadcast news
- relevance model
- sentence retrieval
- document retrieval
- cross language
- language independent
- improvements in retrieval effectiveness
- information retrieval systems
- text mining
- active learning
- vector space
- mixture model
- translation model
- statistical machine translation
- machine translation system
- digital libraries
- statistical language models
- data mining