arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.07530cs.SDeess.AS
收藏

基于动态注意力和相位后处理的生成对抗网络语音增强

Dynamic Attention Based Generative Adversarial Network with Phase Post-Processing for Speech Enhancement

Institute of Acoustics, Chinese Academy of Sciences(中国科学院声学研究所);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学)

Andong Li, Chengshi Zheng, Renhua Peng, Cunhang Fan, Xiaodong Li

摘要:

生成对抗网络(GANs)近年来促进了语音增强的发展。然而,与最先进的模型相比,性能优势仍然有限。在本文中,我们提出了一个强大的动态注意力递归GAN称为DAR GAN的降噪在时间-频率域。与以往的作品不同,我们有几个创新。首先,递归学习,迭代训练协议,用于生成器,它由多个步骤组成。通过在每一步中重用网络,噪声分量以逐步的方式逐渐减少。其次,在降噪模块中引入动态注意力机制,重新调整特征分布。第三,我们利用深度Griffin-Lim算法作为相位后处理的模块,这有助于进一步提高语音质量。在语音银行语料库上的实验结果表明,与现有的基于GAN和非基于GAN的模型相比,本文提出的GAN模型具有更好的性能

英文摘要:

The generative adversarial networks (GANs) have facilitated the development of speech enhancement recently. Nevertheless, the performance advantage is still limited when compared with state-of-the-art models. In this paper, we propose a powerful Dynamic Attention Recursive GAN called DARGAN for noise reduction in the time-frequency domain. Different from previous works, we have several innovations. First, recursive learning, an iterative training protocol, is used in the generator, which consists of multiple steps. By reusing the network in each step, the noise components are progressively reduced in a step-wise manner. Second, the dynamic attention mechanism is deployed, which helps to re-adjust the feature distribution in the noise reduction module. Third, we exploit the deep Griffin-Lim algorithm as the module for phase postprocessing, which facilitates further improvement in speech quality. Experimental results on Voice Bank corpus show that the proposed GAN achieves state-of-the-art performance than previous GAN- and non-GAN-based models

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑