# Towards generalizing deep-audio fake detection networks

arXiv: https://arxiv.org/abs/2305.13033 · HTML: https://mlsanity.com/paper/2305.13033/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 52 references that are in the map.
- First posted on arXiv 22 May 2023.

## Builds on (most cited first, 27 of 27)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [Empirical Evaluation of Rectified Activations in Convolutional Network](https://mlsanity.com/paper/1505.00853/) (2015)
- [Leveraging Frequency Analysis for Deep Fake Image Recognition](https://mlsanity.com/paper/2003.08685/) (2020)
- [MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis](https://mlsanity.com/paper/1910.06711/) (2019)
- [Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram](https://mlsanity.com/paper/1910.11480/) (2019)
- [WaveGlow: A Flow-based Generative Network for Speech Synthesis](https://mlsanity.com/paper/1811.00002/) (2018)
- [BigVGAN: A Universal Neural Vocoder with Large-Scale Training](https://mlsanity.com/paper/2206.04658/) (2022)
- [Do GANs leave artificial fingerprints?](https://mlsanity.com/paper/1812.11842/) (2018)
- [Fourier Spectrum Discrepancies in Deep Network Generated Images](https://mlsanity.com/paper/1911.06465/) (2019)
- [Does Audio Deepfake Detection Generalize?](https://mlsanity.com/paper/2203.16263/) (2022)
- [WaveFake: A Data Set to Facilitate Audio Deepfake Detection](https://mlsanity.com/paper/2111.02813/) (2021)
- [Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speech](https://mlsanity.com/paper/2005.05106/) (2020)
- [On the Frequency Bias of Generative Models](https://mlsanity.com/paper/2111.02447/) (2021)
- [STC Antispoofing Systems for the ASVspoof2019 Challenge](https://mlsanity.com/paper/1904.05576/) (2019)
- [Rethinking CNN Models for Audio Classification](https://mlsanity.com/paper/2007.11154/) (2020)
- [Explaining Deepfake Detection by Analysing Image Matching](https://mlsanity.com/paper/2207.09679/) (2022)
- [Wavelet-Packets for Deepfake Image Analysis and Detection](https://mlsanity.com/paper/2106.09369/) (2021)
- [Avocodo: Generative Adversarial Network for Artifact-free Vocoder](https://mlsanity.com/paper/2206.13404/) (2022)
- [Anisotropic multiresolution analyses for deepfake detection](https://mlsanity.com/paper/2210.14874/) (2022)

## Built on by (most cited first, 2 of 2)

- [Lightweight Model Attribution and Detection of Synthetic Speech via Audio Residual Fingerprints](https://mlsanity.com/paper/2411.14013/) (2024)
- [Tracing Decoder Artifacts for Compact Synthetic Speech Screening](https://mlsanity.com/paper/2609.32050/) (2026)

## Abstract (arXiv)

Today's generative neural networks allow the creation of high-quality synthetic speech at scale. While we welcome the creative use of this new technology, we must also recognize the risks. As synthetic speech is abused for monetary and identity theft, we require a broad set of deepfake identification tools. Furthermore, previous work reported a limited ability of deep classifiers to generalize to unseen audio generators. We study the frequency domain fingerprints of current audio generators. Building on top of the discovered frequency footprints, we train excellent lightweight detectors that generalize. We report improved results on the WaveFake dataset and an extended version. To account for the rapid progress in the field, we extend the WaveFake dataset by additionally considering samples drawn from the novel Avocodo and BigVGAN networks. For illustration purposes, the supplementary material contains audio samples of generator artifacts.