arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1804.02181eess.SPcs.LGstat.ML
收藏

基于生成对抗网络的幅度谱信号重构方法

Generative adversarial network-based approach to signal reconstruction from magnitude spectrograms

University of Tsukuba(筑波大学);NTT Communication Science Laboratories, NTT Corporation(日本电报电话公司NTT通信科学实验室)

Keisuke Oyamada, Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, Nobukatsu Hojo, Hiroyasu Ando

摘要:

在本文中,我们解决的问题,重建时域信号(或相位谱图)单独从幅度谱图。由于幅度谱图不包含相位信息,我们必须恢复或推断相位信息来重建时域信号。Griffin和Lim提出了一种用于处理信号重构问题的广泛使用的方法。这种方法通常需要多次迭代来进行信号重建过程,并且根据输入,它并不总是产生高质量的音频信号。为了克服这些缺点,我们将基于学习的方法应用于信号重建问题,方法是使用深度神经网络对信号重建过程进行建模,并使用生成对抗网络的思想对其进行训练。实验结果表明,我们的方法能够更快地重建信号,具有更高的质量比Griffin-Lim方法。

英文摘要:

In this paper, we address the problem of reconstructing a time-domain signal (or a phase spectrogram) solely from a magnitude spectrogram. Since magnitude spectrograms do not contain phase information, we must restore or infer phase information to reconstruct a time-domain signal. One widely used approach for dealing with the signal reconstruction problem was proposed by Griffin and Lim. This method usually requires many iterations for the signal reconstruction process and depending on the inputs, it does not always produce high-quality audio signals. To overcome these shortcomings, we apply a learning-based approach to the signal reconstruction problem by modeling the signal reconstruction process using a deep neural network and training it using the idea of a generative adversarial network. Experimental evaluations revealed that our method was able to reconstruct signals faster with higher quality than the Griffin-Lim method.

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。

↑