计算机技术与发展2019，Vol.29Issue(2)：152-156,161,6.DOI:10.3969/j.issn.1673-629X.2019.02.032
生成式对抗网络在语音增强方面的研究
Research on Speech Enhancement of Generative Adversarial Networks
摘要
Abstract
Along with the rise of artificial intelligence, all kinds of deep learning models emerge.Generative adversarial networks (GAN) as a deep learning model has become a research hotspot.GAN has been successfully applied in image processing, but its application in speech enhancement is a problem that needs to be studied.GAN's research method in speech enhancement is the same as the essence of GAN, which is based on the construction of two models, namely, generative model and discriminative model, also known as generator and discriminator.They learn and train by mutual competition and confrontation.The ultimate goal of GAN is to generate new data, that is realization of noise removal.The application of GAN in speech enhancement is studied, and the traditional GAN mathematical modeling is proposed for speech enhancement.At the same time, the mathematical model of GAN is improved and sparse factors are added.GAN enhanced speech is compared with other traditional speech enhancement methods.Experiment shows that segSNR and PESQ score of GAN enhanced voice are higher than that of traditional speech enhancement methods, which proves that GAN is more advantageous than other traditional speech enhancement methods.关键词
人工智能/生成式对抗网络/生成器/判别器/语音增强Key words
artificial intelligence/GAN/generator/discriminator/speech enhancement分类
信息技术与安全科学引用本文复制引用
孙成立,王海武..生成式对抗网络在语音增强方面的研究[J].计算机技术与发展,2019,29(2):152-156,161,6.基金项目
国家自然科学基金(61362031,61401259,61761031,61263032) （61362031,61401259,61761031,61263032）
