The IOA System for Deep Noise Suppression Challenge using a Framework Combining Dynamic Attention and Recursive Learning
Year: 2020
Type: preprint
Abstract: This technical report describes our system that is submitted to the Deep Noise Suppression Challenge and presents the results for the non-real-time track. To refine the estimation results stage by stage, we utilize recursive learning, a type of training protocol which aggravates the information through multiple stages with a memory mechanism. The attention generator network is designed to dynamically control the feature distribution of the noise reduction network. To improve the phase recovery accuracy, we take the complex spectral mapping procedure by decoding both real and imaginary spectra. For the final blind test set, the average MOS improvements of the submitted system in noreverb, reverb, and realrec categories are 0.49, 0.24, and 0.36, respectively.
Source: arXiv (Cornell University)
Institutions: Chinese Academy of Sciences, Institute of Acoustics
Language: English
Topic: Speech and Audio Processing
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3025259963