Betray Oneself: A Novel Audio DeepFake Detection Model via Mono-to-Stereo Conversion
Not on the map. Why?
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.
Key facts. Cited by 1 paper 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
23 of 38 references.
References · 23
- 2022Video Diffusion Modelscited by 2,305
- 2019Graph U-Netscited by 492
- 2020End-to-end anti-spoofing with RawNet2cited by 164
- 2022ADD 2022: the First Audio Deep Synthesis Detection Challengecited by 96
- 2021End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detectioncited by 70
- 2020One-class Learning Towards Synthetic Voice Spoofing Detectioncited by 61
- 2021A Comparative Study on Recent Neural Spoofing Countermeasures for Synthetic Speech Detectioncited by 56
- 2019STC Antispoofing Systems for the ASVspoof2019 Challengecited by 51
- 2020Replay and Synthetic Speech Detection with Res2net Architecturecited by 39
- 2021Towards End-to-End Synthetic Speech Detectioncited by 38
- 2020The Elements of End-to-end Deep Face Recognition: A Survey of Recent Advancescited by 32
- 2020Expressive TTS Training with Frame and Style Reconstruction Losscited by 30
11 more
- 2020Tandem Assessment of Spoofing Countermeasures and Automatic Speaker Verification: Fundamentalscited by 22
- 2018t-DCF: a Detection Cost Function for the Tandem Assessment of Spoofing Countermeasures and Automatic Speaker Verificationcited by 19
- 2021Channel-wise Gated Res2Net: Towards Robust Detection of Synthetic Speech Attackscited by 18
- 2021Graph Attention Networks for Anti-Spoofingcited by 17
- 2020Spoofing Attack Detection using the Non-linear Fusion of Sub-band Classifierscited by 9
- 2020GraphSpeech: Syntax-Aware Graph Attention Network For Neural Speech Synthesiscited by 9
- 2021Partially-Connected Differentiable Architecture Search for Deepfake and Spoofing Detectioncited by 9
- 2021Graph attentive feature aggregation for text-independent speaker verificationcited by 4
- 2023Deepfake Detection Analyzing Hybrid Dataset Utilizing CNN and SVMcited by 3
- 2022Objective Assessment of Spatial Audio Quality using Directional Loudness Mapscited by 2
- 2021A Training Framework for Stereo-Aware Speech Enhancement using Deep Neural Networkscited by 1
Built on by
Citing papers per year: 2024: 1.
1 paper.