An improved two-stage mixed language model approach for handling out-of-vocabulary words in large vocabulary continuous speech recognition.
Bert RéveilKris DemuynckJean-Pierre MartensPublished in: Comput. Speech Lang. (2014)
Keyphrases
- out of vocabulary
- language model
- n gram
- language modeling
- spoken document retrieval
- document retrieval
- information retrieval
- probabilistic model
- query expansion
- speech recognition
- retrieval model
- test collection
- context sensitive
- query terms
- word segmentation
- pseudo relevance feedback
- information retrieval systems
- automatic speech recognition
- translation model
- machine learning
- broadcast news
- document representation
- vector space model
- information extraction