Real-Time One-Pass Decoder for Speech Recognition Using LSTM Language Models.
Javier JorgeAdrià GiménezJavier Iranzo-SánchezJorge CiveraAlbert SanchísAlfons JuanPublished in: INTERSPEECH (2019)
Keyphrases
- language model
- speech recognition
- language modeling
- finite state transducers
- word error rate
- n gram
- probabilistic model
- retrieval model
- information retrieval
- language modelling
- query expansion
- test collection
- statistical language models
- automatic speech recognition
- speech signal
- spoken term detection
- document retrieval
- query terms
- pseudo relevance feedback
- language models for information retrieval
- language model for information retrieval
- smoothing methods
- relevance model
- vector space model
- translation model
- document ranking
- context sensitive
- ad hoc information retrieval
- error rate
- broadcast news
- out of vocabulary
- handwriting recognition
- audio visual
- bayesian networks
- feature selection