End-to-End Dereverberation, Beamforming, and Speech Recognition with Improved Numerical Stability and Advanced Frontend.
Wangyou ZhangChristoph BöddekerShinji WatanabeTomohiro NakataniMarc DelcroixKeisuke KinoshitaTsubasa OchiaiNaoyuki KamoReinhold Haeb-UmbachYanmin QianPublished in: CoRR (2021)
Keyphrases
- end to end
- speech recognition
- numerical stability
- hidden markov models
- speech signal
- language model
- computational efficiency
- pattern recognition
- speech synthesis
- speech recognizer
- automatic speech recognition
- zernike moments
- convergence rate
- noisy environments
- speaker identification
- speech recognition systems
- neural network
- multiresolution
- computer vision
- recursive least squares
- frequency domain