1. Improving deep speech denoising by Noisy2Noisy signal mapping
- Author
-
Nasser Kehtarnavaz, Arian Azarang, and Nasim Alamdari
- Subjects
Signal Processing (eess.SP) ,FOS: Computer and information sciences ,Sound (cs.SD) ,Acoustics and Ultrasonics ,Computer science ,business.industry ,Microphone ,Deep learning ,Speech recognition ,Mode (statistics) ,Computer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing) ,Signal mapping ,Signal ,Convolutional neural network ,Computer Science - Sound ,Audio and Speech Processing (eess.AS) ,Computer Science::Sound ,FOS: Electrical engineering, electronic engineering, information engineering ,Speech denoising ,Artificial intelligence ,Electrical Engineering and Systems Science - Signal Processing ,business ,Electrical Engineering and Systems Science - Audio and Speech Processing - Abstract
Existing deep learning-based speech denoising approaches require clean speech signals to be available for training. This paper presents a deep learning-based approach to improve speech denoising in real-world audio environments by not requiring the availability of clean speech signals as reference in training mode. A fully convolutional neural network is trained by using two noisy realizations of the same speech signal, one used as the input and the other as the target of the network. Two noisy realizations of the same speech signal are generated by using a mid-side stereo microphone. Extensive experimentations are conducted to show the superiority of the developed deep speech denoising approach over the conventional supervised deep speech denoising approach based on four commonly used performance metrics as well as a subjective testing.
- Published
- 2021
- Full Text
- View/download PDF