arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.02011cs.SDcs.AIeess.AS
收藏

基于循环一致生成对抗网络的两级复杂网络语音增强

A Two-stage Complex Network using Cycle-consistent Generative Adversarial Networks for Speech Enhancement

Communication University of China(中国传媒大学);Institute of Acoustics, Chinese Academy of Sciences(中国科学院声学研究所);University of Chinese Academy of Sciences(中国科学院大学)

Guochen Yu, Yutian Wang, Hui Wang, Qin Zhang, Chengshi Zheng

摘要:

循环一致的生成对抗网络(CycleGAN)已经显示出其在语音增强(SE)方面的良好性能,而这些基于CycleGAN的SE系统的一个棘手的缺点是噪声分量在整个循环中传播并且不能完全消除。此外,传统的基于CycleGAN的SE系统仅估计频谱幅度,而相位不变。受多阶段学习概念的启发,本文提出了一种新的两阶段去噪系统,该系统结合了基于CycleGAN的幅度增强网络和随后的复杂频谱细化网络。具体来说,在第一阶段,基于CycleGAN的模型只负责估计幅度,随后将其与原始噪声相位耦合以获得粗略增强的复频谱。在此之后,第二阶段应用于进一步抑制残余噪声分量并通过复谱映射网络估计干净相位,复谱映射网络是由复2D卷积/反卷积和复时频注意块组成的纯复值网络。在两个公开数据集上的实验结果表明,该方法在各种评估指标方面,特别是在背景噪声抑制方面,始终优于以前的单阶段CycleGAN和其他最先进的SE系统。

英文摘要:

Cycle-consistent generative adversarial networks (CycleGAN) have shown their promising performance for speech enhancement (SE), while one intractable shortcoming of these CycleGAN-based SE systems is that the noise components propagate throughout the cycle and cannot be completely eliminated. Additionally, conventional CycleGAN-based SE systems only estimate the spectral magnitude, while the phase is unaltered. Motivated by the multi-stage learning concept, we propose a novel two-stage denoising system that combines a CycleGAN-based magnitude enhancing network and a subsequent complex spectral refining network in this paper. Specifically, in the first stage, a CycleGAN-based model is responsible for only estimating magnitude, which is subsequently coupled with the original noisy phase to obtain a coarsely enhanced complex spectrum. After that, the second stage is applied to further suppress the residual noise components and estimate the clean phase by a complex spectral mapping network, which is a pure complex-valued network composed of complex 2D convolution/deconvolution and complex temporal-frequency attention blocks. Experimental results on two public datasets demonstrate that the proposed approach consistently surpasses previous one-stage CycleGANs and other state-of-the-art SE systems in terms of various evaluation metrics, especially in background noise suppression.

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。

↑