Full-Sum Decoding for Hybrid Hmm Based Speech Recognition Using LSTM Language Model.
Wei ZhouRalf SchlüterHermann NeyPublished in: ICASSP (2020)
Keyphrases
- language model
- speech recognition
- word error rate
- language modeling
- hidden markov models
- automatic speech recognition
- document retrieval
- probabilistic model
- speech signal
- retrieval model
- mixture model
- n gram
- test collection
- query expansion
- information retrieval
- query terms
- error rate
- language modelling
- context sensitive
- document length
- pseudo relevance feedback
- statistical machine translation
- document ranking
- dependency structure
- ad hoc information retrieval
- vector space model
- language models for information retrieval
- translation model
- statistical language models
- language model for information retrieval
- generative model
- smoothing methods
- handwriting recognition
- relevance model