Integrate Lattice-Free MMI into End-to-End Speech Recognition.
Jinchuan TianJianwei YuChao WengYuexian ZouDong YuPublished in: CoRR (2022)
Keyphrases
- end to end
- speech recognition
- automatic speech recognition
- pattern recognition
- hidden markov models
- language model
- speech signal
- speech processing
- isolated word
- speech recognition systems
- speech recognition technology
- congestion control
- noisy environments
- speech synthesis
- speaker identification
- speaker independent
- speech recognizers
- broadcast news
- maximum likelihood
- image processing