计算机工程与应用2019，Vol.55Issue(20)：240-244,270,6.DOI:10.3778/j.issn.1002-8331.1806-0468
基于生成对抗网络的音频音质提升方法
Audio Enhancement Based on Generative Adversarial Nets
摘要
Abstract
For the convenience of network transmission as well as the ease of server harddisks’burden, large amount of audio files are compressed, while the audio quality is decreased. This paper proposes an audio quality enhancement algorithm-ASRGAN(Audio Super Resolution Generative Adversarial Networks)-for MPEG-1 Layer 3 files. In this algorithm, the generative network and discrimitive network form a competitive learning, and alternative weighting training is used. Com-bined with dilation convolution and bidirectional recurrent neural network which evidently enhances the network’s ability in disposing of overlong sequence, the optimal audio quality restoration network is finally set up. This algorithm can reduce the network bandwidth and storage space used by audio files and meanwhile maintain a decent audio quality.关键词
生成对抗网络(GAN)/音质提升/模型压缩Key words
Generative Adversarial Nets(GAN)/audio enhancement/model compression分类
信息技术与安全科学引用本文复制引用
张逸,谷毅,韩芳,王直杰..基于生成对抗网络的音频音质提升方法[J].计算机工程与应用,2019,55(20):240-244,270,6.基金项目
国家自然科学基金(No.11572084,No.11472061) （No.11572084,No.11472061）
中央高校基本科研业务费专项资金、东华大学"励志计划"(No.18D210402). （No.18D210402）
