N-gram Approximation of Latent Words Language Models for Domain Robust Automatic Speech Recognition.
Ryo MasumuraTaichi AsamiTakanobu ObaHirokazu MasatakiSumitaka SakauchiSatoshi TakahashiPublished in: IEICE Trans. Inf. Syst. (2016)
Keyphrases
- n gram
- language model
- speech recognition
- automatic speech recognition
- word error rate
- language modeling
- language modelling
- speech signal
- information retrieval
- bag of words
- language independent
- retrieval model
- probabilistic model
- document retrieval
- vector space model
- part of speech
- query expansion
- word segmentation
- word recognition
- viterbi algorithm
- broadcast news
- test collection
- document representation
- hidden markov models
- out of vocabulary
- statistical language modeling
- term dependencies
- handwriting recognition
- query terms
- pattern recognition
- okapi bm
- bayesian networks