Abstract
We present a method for audio denoising that combines processing done in both the time domain and the time-frequency domain. Given a noisy audio clip, the method trains a deep neural network to fit this signal. Since the fitting is only partly successful and is able to better capture the underlying clean signal than the noise, the output of the network helps to disentangle the clean audio from the rest of the signal. The method is completely unsupervised and only trains on the specific audio clip that is being denoised. Our experiments demonstrate favorable performance in comparison to the literature methods, and our code and audio samples are available at https: //github.com/mosheman5/DNP. Index Terms: Audio denoising; Unsupervised learning
Abstract (translated)
我们提出了一种音频去噪方法,它结合了在时间域和时间频率域进行的处理。给出一个有噪声的音频片段,该方法训练一个深度神经网络来适应这个信号。由于安装只取得了部分成功,并且能够比噪声更好地捕获底层的干净信号,因此网络的输出有助于将干净的音频与信号的其余部分分离开来。该方法是完全无监督的,只训练特定的音频剪辑,正在去噪。与文献方法相比,我们的实验显示了良好的性能,我们的代码和音频样本可在https://github.com/mosheman5/dnp上获得。索引项:音频去噪;无监督学习
URL
https://arxiv.org/abs/1904.07612