Synchronous Transformers for end-to-end Speech Recognition.
Zhengkun TianJiangyan YiYe BaiJianhua TaoShuai ZhangZhengqi WenPublished in: ICASSP (2020)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- language model
- speech signal
- speech processing
- speech recognizer
- automatic speech recognition
- congestion control
- pattern recognition
- speech recognition systems
- speech synthesis
- noisy environments
- speaker independent
- speech retrieval
- speech recognition technology
- speaker identification
- speaker dependent
- visual information
- multiresolution
- multimedia
- speech recognizers