Language model fusion for streaming end to end speech recognition.
Rodrigo CabreraXiaofeng LiuMohammadreza GhodsiZebulun MattesonEugene WeinsteinAnjuli KannanPublished in: CoRR (2021)
Keyphrases
- end to end
- speech recognition
- language model
- scalable video
- language modeling
- probabilistic model
- n gram
- information retrieval
- document retrieval
- automatic speech recognition
- mixture model
- retrieval model
- test collection
- speech signal
- query expansion
- noisy environments
- word error rate
- data streams
- video streaming
- speech recognition systems
- relevance model
- query terms
- transport protocol
- image fusion
- translation model
- information extraction
- hidden markov models