End-to-End Far-Field Speech Recognition with Unified Dereverberation and Beamforming.
Wangyou ZhangAswin Shanmugam SubramanianXuankai ChangShinji WatanabeYanmin QianPublished in: INTERSPEECH (2020)
Keyphrases
- end to end
- speech recognition
- speech signal
- hidden markov models
- speech enhancement
- noisy environments
- speech synthesis
- language model
- pattern recognition
- automatic speech recognition
- speech processing
- congestion control
- speaker identification
- multipath
- speech recognition systems
- frequency domain
- speaker independent
- speech recognizer
- isolated word
- speech recognition technology
- information retrieval
- subband
- video data
- multimedia