Internal Language Model Training for Domain-Adaptive End-To-End Speech Recognition.
Zhong MengNaoyuki KandaYashesh GaurSarangarajan ParthasarathyEric SunLiang LuXie ChenJinyu LiYifan GongPublished in: ICASSP (2021)
Keyphrases
- speech recognition
- end to end
- language model
- language modeling
- isolated word
- probabilistic model
- n gram
- retrieval model
- automatic speech recognition
- document retrieval
- information retrieval
- speech signal
- speech recognizer
- acoustic models
- word error rate
- handwriting recognition
- query expansion
- test collection
- hidden markov models
- mixture model
- query terms
- translation model
- smoothing methods
- pattern recognition
- speech recognition systems
- speaker independent
- noisy environments
- image processing
- mobile devices
- computer vision