# Discriminating real and synthetic super-resolved audio samples using embedding-based classifiers

arXiv: https://arxiv.org/abs/2601.03443 · HTML: https://mlsanity.com/paper/2601.03443/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 18 of its 27 references that are in the map.
- First posted on arXiv 6 Jan 2026.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 18 of 18)

- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Improved Precision and Recall Metric for Assessing Generative Models](https://mlsanity.com/paper/1904.06991/) (2019)
- [Assessing Generative Models via Precision and Recall](https://mlsanity.com/paper/1806.00035/) (2018)
- [Are GANs Created Equal? A Large-Scale Study](https://mlsanity.com/paper/1711.10337/) (2017)
- [Fr'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms](https://mlsanity.com/paper/1812.08466/) (2018)
- [FMA: A Dataset For Music Analysis](https://mlsanity.com/paper/1612.01840/) (2016)
- [High Fidelity Speech Synthesis with Adversarial Networks](https://mlsanity.com/paper/1909.11646/) (2019)
- [AudioSR: Versatile Audio Super-resolution at Scale](https://mlsanity.com/paper/2309.07314/) (2023)
- [Audio Super Resolution using Neural Networks](https://mlsanity.com/paper/1708.00853/) (2017)
- [Privacy-Preserving Adversarial Representation Learning in ASR: Reality or Illusion?](https://mlsanity.com/paper/1911.04913/) (2019)
- [Real-time Speech Frequency Bandwidth Extension](https://mlsanity.com/paper/2010.10677/) (2020)
- [FLowHigh: Towards Efficient and High-Quality Audio Super-Resolution with Single-Step Flow Matching](https://mlsanity.com/paper/2501.04926/) (2025)
- [BEHM-GAN: Bandwidth Extension of Historical Music using Generative Adversarial Networks](https://mlsanity.com/paper/2204.06478/) (2022)
- [Bandwidth Extension on Raw Audio via Generative Adversarial Networks](https://mlsanity.com/paper/1903.09027/) (2019)
- [FlashSR: One-step Versatile Audio Super-resolution via Diffusion Distillation](https://mlsanity.com/paper/2501.10807/) (2025)
- [Adversarial Representation Learning for Robust Privacy Preservation in Audio](https://mlsanity.com/paper/2305.00011/) (2023)

## Abstract (arXiv)

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→ 16~kHz) and full-band (16→ 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.