Keep Decoding Parallel with Effective Knowledge Distillation from Language Models to End-to-end Speech Recognisers.
Michael HentschelYuta NishikawaTatsuya KomatsuYusuke FujitaPublished in: CoRR (2024)
Keyphrases
- end to end
- language model
- speech recognition
- language modeling
- probabilistic model
- n gram
- document retrieval
- language modelling
- word error rate
- retrieval model
- spoken term detection
- statistical language models
- automatic speech recognition
- admission control
- test collection
- document ranking
- congestion control
- speech signal
- handwriting recognition
- application layer
- scalable video
- out of vocabulary
- transport layer
- query expansion
- language models for information retrieval
- information retrieval
- vector space model
- context sensitive