Neural-FST Class Language Model for End-to-End Speech Recognition.
Antoine BruguierDuc LeRohit PrabhavalkarDangna LiZhe LiuBo WangEun ChangFuchun PengOzlem KalinliMichael L. SeltzerPublished in: ICASSP (2022)
Keyphrases
- speech recognition
- end to end
- language model
- language modeling
- n gram
- probabilistic model
- information retrieval
- automatic speech recognition
- query expansion
- document retrieval
- test collection
- speech signal
- noisy environments
- word error rate
- neural network
- hidden markov models
- mixture model
- retrieval model
- query terms
- handwriting recognition
- speech recognition systems
- non stationary
- image processing