# Betray Oneself: A Novel Audio DeepFake Detection Model via Mono-to-Stereo Conversion

arXiv: https://arxiv.org/abs/2305.16353 · HTML: https://mlsanity.com/paper/2305.16353/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 38 references that are in the map.
- First posted on arXiv 25 May 2023.

## Builds on (most cited first, 23 of 23)

- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [Graph U-Nets](https://mlsanity.com/paper/1905.05178/) (2019)
- [End-to-end anti-spoofing with RawNet2](https://mlsanity.com/paper/2011.01108/) (2020)
- [ADD 2022: the First Audio Deep Synthesis Detection Challenge](https://mlsanity.com/paper/2202.08433/) (2022)
- [End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detection](https://mlsanity.com/paper/2107.12710/) (2021)
- [One-class Learning Towards Synthetic Voice Spoofing Detection](https://mlsanity.com/paper/2010.13995/) (2020)
- [A Comparative Study on Recent Neural Spoofing Countermeasures for Synthetic Speech Detection](https://mlsanity.com/paper/2103.11326/) (2021)
- [STC Antispoofing Systems for the ASVspoof2019 Challenge](https://mlsanity.com/paper/1904.05576/) (2019)
- [Replay and Synthetic Speech Detection with Res2net Architecture](https://mlsanity.com/paper/2010.15006/) (2020)
- [Towards End-to-End Synthetic Speech Detection](https://mlsanity.com/paper/2106.06341/) (2021)
- [The Elements of End-to-end Deep Face Recognition: A Survey of Recent Advances](https://mlsanity.com/paper/2009.13290/) (2020)
- [Expressive TTS Training with Frame and Style Reconstruction Loss](https://mlsanity.com/paper/2008.01490/) (2020)
- [Tandem Assessment of Spoofing Countermeasures and Automatic Speaker Verification: Fundamentals](https://mlsanity.com/paper/2007.05979/) (2020)
- [t-DCF: a Detection Cost Function for the Tandem Assessment of Spoofing Countermeasures and Automatic Speaker Verification](https://mlsanity.com/paper/1804.09618/) (2018)
- [Channel-wise Gated Res2Net: Towards Robust Detection of Synthetic Speech Attacks](https://mlsanity.com/paper/2107.08803/) (2021)
- [Graph Attention Networks for Anti-Spoofing](https://mlsanity.com/paper/2104.03654/) (2021)
- [Spoofing Attack Detection using the Non-linear Fusion of Sub-band Classifiers](https://mlsanity.com/paper/2005.10393/) (2020)
- [GraphSpeech: Syntax-Aware Graph Attention Network For Neural Speech Synthesis](https://mlsanity.com/paper/2010.12423/) (2020)
- [Partially-Connected Differentiable Architecture Search for Deepfake and Spoofing Detection](https://mlsanity.com/paper/2104.03123/) (2021)
- [Graph attentive feature aggregation for text-independent speaker verification](https://mlsanity.com/paper/2112.12343/) (2021)
- [Deepfake Detection Analyzing Hybrid Dataset Utilizing CNN and SVM](https://mlsanity.com/paper/2302.10280/) (2023)
- [Objective Assessment of Spatial Audio Quality using Directional Loudness Maps](https://mlsanity.com/paper/2212.01451/) (2022)
- [A Training Framework for Stereo-Aware Speech Enhancement using Deep Neural Networks](https://mlsanity.com/paper/2112.04939/) (2021)

## Built on by (most cited first, 1 of 1)

- [SecureSpectra: Safeguarding Digital Identity from Deep Fake Threats via Intelligent Signatures](https://mlsanity.com/paper/2407.00913/) (2024)

## Abstract (arXiv)

Audio Deepfake Detection (ADD) aims to detect the fake audio generated by text-to-speech (TTS), voice conversion (VC) and replay, etc., which is an emerging topic. Traditionally we take the mono signal as input and focus on robust feature extraction and effective classifier design. However, the dual-channel stereo information in the audio signal also includes important cues for deepfake, which has not been studied in the prior work. In this paper, we propose a novel ADD model, termed as M2S-ADD, that attempts to discover audio authenticity cues during the mono-to-stereo conversion process. We first projects the mono to a stereo signal using a pretrained stereo synthesizer, then employs a dual-branch neural architecture to process the left and right channel signals, respectively. In this way, we effectively reveal the artifacts in the fake audio, thus improve the ADD performance. The experiments on the ASVspoof2019 database show that M2S-ADD outperforms all baselines that input mono. We release the source code at urlhttps://github.com/AI-S2-Lab/M2S-ADD.