High speed spoken term detection by combination of n-gram array of a syllable lattice and LVCSR result for NTCIR-SpokenDoc.
Keisuke IwamiSeiichi NakagawaPublished in: NTCIR (2011)
Keyphrases
- n gram
- spoken term detection
- language model
- high speed
- test collection
- out of vocabulary
- language modeling
- language independent
- information retrieval
- bag of words
- speech recognition
- probabilistic model
- document retrieval
- retrieval model
- text classification
- query expansion
- retrieval effectiveness
- viterbi algorithm
- part of speech
- broadcast news
- word level
- word segmentation
- finite state transducers
- relevant documents
- pseudo relevance feedback
- retrieval systems
- bayesian networks
- search engine