论文标题
使用生成对抗网络对重压的音乐音频的随机恢复
Stochastic Restoration of Heavily Compressed Musical Audio using Generative Adversarial Networks
论文作者
论文摘要
有损音频编解码器通过删除在人类感知中听不清的信息来压缩（和解压缩）数字音频流。在高压率下，此类编解码器可能会在音频信号中引入各种损伤。许多作品解决了使用深度学习技术的音频增强和压缩伪像的问题的问题。但是，只有少数作品可以解决音乐领域中严重压缩的音频信号的恢复。在这种情况下，没有独特的解决方案来恢复原始信号。因此，在这项研究中，我们针对此任务测试了生成对抗网络（GAN）体系结构的随机发生器。这样的随机发电机以高度压缩的音乐音频信号为条件，有一天可能会与高质量的发行版产生无法区分的输出。因此，本研究可能会产生对更有效的音乐数据存储和传输的见解。我们以16、32和64 kbit/s训练在MP3压缩音频信号上训练随机和确定性的发电机。我们对利用客观指标和听力测试的不同实验进行了广泛的评估。我们发现，模型可以改善16和32 kbit/s的MP3版本的音频信号的质量，并且随机发电机能够生成比确定性生成器的输出更接近原始信号的输出。
Lossy audio codecs compress (and decompress) digital audio streams by removing information that tends to be inaudible in human perception. Under high compression rates, such codecs may introduce a variety of impairments in the audio signal. Many works have tackled the problem of audio enhancement and compression artifact removal using deep learning techniques. However, only a few works tackle the restoration of heavily compressed audio signals in the musical domain. In such a scenario, there is no unique solution for the restoration of the original signal. Therefore, in this study, we test a stochastic generator of a Generative Adversarial Network (GAN) architecture for this task. Such a stochastic generator, conditioned on highly compressed musical audio signals, could one day generate outputs indistinguishable from high-quality releases. Therefore, the present study may yield insights into more efficient musical data storage and transmission. We train stochastic and deterministic generators on MP3-compressed audio signals with 16, 32, and 64 kbit/s. We perform an extensive evaluation of the different experiments utilizing objective metrics and listening tests. We find that the models can improve the quality of the audio signals over the MP3 versions for 16 and 32 kbit/s and that the stochastic generators are capable of generating outputs that are closer to the original signals than those of the deterministic generators.
