Viterbi Approximation of Latent Words Language Models for Automatic Speech Recognition.
Ryo MasumuraTaichi AsamiTakanobu ObaHirokazu MasatakiSumitaka SakauchiPublished in: J. Inf. Process. (2019)
Keyphrases
- language model
- word error rate
- automatic speech recognition
- speech recognition
- n gram
- hidden markov models
- spoken words
- speech corpus
- viterbi algorithm
- word recognition
- language modeling
- conversational speech
- probabilistic model
- document representation
- speech signal
- error rate
- broadcast news
- out of vocabulary
- multiword
- document retrieval
- statistical language modeling
- retrieval model
- language modelling
- information retrieval
- spontaneous speech
- language independent
- test collection
- passage retrieval
- query expansion
- speech sounds
- smoothing methods
- spoken document retrieval
- okapi bm
- text documents
- spoken term detection