Speech Dereverberation Using Variational Autoencoders.
Deepak BabyHervé BourlardPublished in: ICASSP (2021)
Keyphrases
- speech recognition
- denoising
- recognition engine
- image segmentation
- speech signal
- speech synthesis
- endpoint detection
- text to speech
- spoken language
- automatic speech recognition
- automatic speech recognition systems
- speaker recognition
- broadcast news
- optical flow computation
- multi stream
- audio visual
- noisy environments
- methods in computer vision
- machine learning