Improving Hybrid CTC/Attention End-to-End Speech Recognition with Pretrained Acoustic and Language Models.
Keqi DengSongjun CaoYike ZhangLong MaPublished in: ASRU (2021)
Keyphrases
- end to end
- speech recognition
- language model
- speech recognition systems
- speaker independent
- speech recognizers
- language modeling
- acoustic models
- n gram
- speech recognizer
- document retrieval
- probabilistic model
- automatic speech recognition
- noisy speech
- speech signal
- test collection
- information retrieval
- retrieval model
- speech synthesis
- word error rate
- mixture model
- query terms
- handwriting recognition
- noisy environments
- acoustic features
- hidden markov models
- query expansion
- machine learning