Posterior-based out of vocabulary word detection in telephone speech.
Stefan KombrinkLukás BurgetPavel MatejkaMartin KarafiátHynek HermanskyPublished in: INTERSPEECH (2009)
Keyphrases
- out of vocabulary
- broadcast news
- spoken document retrieval
- speech recognizer
- language model
- word segmentation
- n gram
- named entity recognition
- spoken term detection
- cross language information retrieval
- speech recognition
- query words
- named entities
- query terms
- spoken language
- automatic speech recognition
- information retrieval
- probabilistic model
- parallel corpora
- cross lingual
- machine translation
- hand crafted
- language modeling
- word recognition
- language processing
- test collection
- information extraction
- language independent
- video retrieval
- maximum entropy
- question answering
- information retrieval systems
- search engine