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: ICASSP (2021)
Keyphrases
- end to end
- speech recognition
- numerical stability
- hidden markov models
- language model
- automatic speech recognition
- speech recognizer
- speech signal
- speech synthesis
- speech recognition systems
- computational efficiency
- convergence rate
- noisy environments
- speaker identification
- linear algebra
- zernike moments
- speech enhancement
- image processing
- signal processing