A Fast Convolutional Self-attention Based Speech Dereverberation Method for Robust Speech Recognition.
Nan LiMeng GeLongbiao WangJianwu DangPublished in: ICONIP (3) (2019)
Keyphrases
- speech recognition
- speech recognizer
- speaker recognition
- automatic speech recognition
- speech recognizers
- speech signal
- noisy environments
- hidden markov models
- speaker identification
- pattern recognition
- hybrid method
- speech synthesis
- speech recognition technology
- language model
- error rate
- feature set
- probabilistic model
- speech recognition errors
- noisy speech
- machine learning