End-to-End Dereverberation, Beamforming, and Speech Recognition in a Cocktail Party.
Wangyou ZhangXuankai ChangChristoph BöddekerTomohiro NakataniShinji WatanabeYanmin QianPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2022)
Keyphrases
- end to end
- speech recognition
- speech signal
- speech enhancement
- hidden markov models
- speech synthesis
- language model
- noisy environments
- speech processing
- congestion control
- multipath
- frequency domain
- automatic speech recognition
- pattern recognition
- speech recognition systems
- speech recognizer
- speech recognition technology
- sound source
- background noise
- wavelet transform
- speaker dependent