Sub-word modeling of out of vocabulary words in spoken term detection.
Igor SzökeLukás BurgetJan CernockýMichal FapsoPublished in: SLT (2008)
Keyphrases
- out of vocabulary
- spoken term detection
- word segmentation
- n gram
- language model
- broadcast news
- cross language information retrieval
- named entity recognition
- cross lingual
- query terms
- hand crafted
- parallel corpora
- named entities
- information extraction
- language modeling
- term frequency
- query translation
- word recognition
- previously unseen
- machine translation
- retrieval model
- word level
- linguistic features
- document representation
- language independent
- video retrieval
- document retrieval
- speech recognition
- text classification
- natural language processing