UNet++-Based Multi-Channel Speech Dereverberation and Distant Speech Recognition.
Tuo ZhaoYunxin ZhaoShaojun WangMei HanPublished in: ISCSLP (2021)
Keyphrases
- speech recognition
- multi channel
- speech signal
- speech synthesis
- automatic speech recognition
- speech recognizer
- language model
- speech recognition systems
- speech processing
- hidden markov models
- speech recognition technology
- speaker identification
- single channel
- noisy environments
- word error rate
- isolated word
- speech recognizers
- pattern recognition
- speaker independent
- recognition engine
- speaker dependent
- noisy speech
- acoustic models
- cepstral coefficients
- speech recognition errors
- image processing
- vocal tract
- broadcast news
- neural network