Many audio processing tasks require perceptual assessment. The ``gold standard`` of obtaining human judgments is time-consuming, expensive, and cannot be used as an optimization criterion. On the other hand, automated metrics are efficient to compute but often correlate poorly with human judgment, particularly for audio differences at the threshold of human detection. In this work, we construct a metric by fitting a deep neural network to a new large dataset of crowdsourced human judgments. Subjects are prompted to answer a straightforward, objective question: are two recordings identical or not? These pairs are algorithmically generated under a variety of perturbations, including noise, reverb, and compression artifacts; the perturbation space is probed with the goal of efficiently identifying the just-noticeable difference (JND) level of the subject. We show that the resulting learned metric is well-calibrated with human judgments, outperforming baseline methods. Since it is a deep network, the metric is differentiable, making it suitable as a loss function for other tasks. Thus, simply replacing an existing loss (e.g., deep feature loss) with our metric yields significant improvement in a denoising network, as measured by subjective pairwise comparison.

中文翻译：

---

从明显的差异中学习到的可区分的感知音频指标

许多音频处理任务需要感知评估。获得人工判断的“黄金标准”耗时、昂贵，不能作为优化标准。另一方面，自动化指标的计算效率很高，但通常与人类判断的相关性较差，特别是对于人类检测阈值处的音频差异。在这项工作中，我们通过将深度神经网络拟合到众包人类判断的新大型数据集来构建度量。提示受试者回答一个直接、客观的问题：两个录音是否相同？这些对是在各种扰动下通过算法生成的，包括噪声、混响和压缩伪影；探测扰动空间的目的是有效识别主体的刚好可察觉差异 (JND) 水平。我们表明，由此产生的学习度量与人类判断进行了很好的校准，优于基线方法。由于它是一个深度网络，度量是可微的，使其适合作为其他任务的损失函数。因此，通过主观成对比较来衡量，简单地用我们的度量替换现有的损失（例如，深度特征损失）可以显着改善去噪网络。