Abstract
Generative adversarial networks (GANs) and diffusion models have recently achieved state-of-the-art performance in audio super-resolution (ADSR), producing perceptually convincing wideband audio from narrowband inputs. However, existing evaluations primarily rely on signal-level or perceptual metrics, leaving open the question of how closely the distributions of synthetic super-resolved and real wideband audio match. Here we address this problem by analyzing the separability of real and super-resolved audio in various embedding spaces. We consider both middle-band ($4\to 16$~kHz) and full-band ($16\to 48$~kHz) upsampling tasks for speech and music, training linear classifiers to distinguish real from synthetic samples based on multiple types of audio embeddings. Comparisons with objective metrics and subjective listening tests reveal that embedding-based classifiers achieve near-perfect separation, even when the generated audio attains high perceptual quality and state-of-the-art metric scores. This behavior is consistent across datasets and models, including recent diffusion-based approaches, highlighting a persistent gap between perceptual quality and true distributional fidelity in ADSR models.
Abstract (translated)
生成对抗网络（GANs）和扩散模型近期在音频超分辨率（ADSR）领域取得了最先进的性能，能够从窄带输入中生成感知上逼真的宽带音频。然而，现有的评估主要依赖于信号级或感知度量标准，这留下了合成增强的音频与真实宽带音频分布之间匹配程度的问题未解。在这里，我们通过分析不同嵌入空间中实际和超分辨率音频的可分离性来解决这个问题。我们考虑了从中间带（4到16 kHz）到全频带（16到48 kHz）的声音和音乐上采样任务，在多种类型的音频嵌入基础上训练线性分类器，以区分真实样本与合成样本。通过客观度量标准以及主观听觉测试的比较显示，基于嵌入的方法能够实现近乎完美的分离，即使生成的音频达到了很高的感知质量和最先进的指标评分也是如此。这种行为在不同的数据集和模型中（包括最近的扩散方法）是一致的，这突显了感知质量与真实分布保真度之间持久存在的差距存在于ADSR模型中。
URL
https://arxiv.org/abs/2601.03443
