# Dual-Granularity Orthogonal Disentanglement for Generalizable Audio Deepfake Detection

arXiv: https://arxiv.org/abs/2606.16532 · HTML: https://mlsanity.com/paper/2606.16532/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 36 references that are in the map.
- First posted on arXiv 15 Jun 2026.

## Builds on (most cited first, 29 of 29)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone](https://mlsanity.com/paper/2112.02418/) (2021)
- [AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks](https://mlsanity.com/paper/2110.01200/) (2021)
- [End-to-end anti-spoofing with RawNet2](https://mlsanity.com/paper/2011.01108/) (2020)
- [ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection](https://mlsanity.com/paper/2109.00537/) (2021)
- [Does Audio Deepfake Detection Generalize?](https://mlsanity.com/paper/2203.16263/) (2022)
- [Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation](https://mlsanity.com/paper/2202.12233/) (2022)
- [An Overview of Voice Conversion and its Challenges: From Statistical Modeling to Deep Learning](https://mlsanity.com/paper/2008.03648/) (2020)
- [ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers](https://mlsanity.com/paper/2204.09224/) (2022)
- [On Disentangling Spoof Trace for Generic Face Anti-Spoofing](https://mlsanity.com/paper/2007.09273/) (2020)
- [STC Antispoofing Systems for the ASVspoof2019 Challenge](https://mlsanity.com/paper/1904.05576/) (2019)
- [Audio Deepfake Detection: A Survey](https://mlsanity.com/paper/2308.14970/) (2023)
- [Any-to-Many Voice Conversion with Location-Relative Sequence-to-Sequence Modeling](https://mlsanity.com/paper/2009.02725/) (2020)
- [The Vicomtech Audio Deepfake Detection System based on Wav2Vec2 for the 2022 ADD Challenge](https://mlsanity.com/paper/2203.01573/) (2022)
- [Speech Emotion Recognition with Co-Attention based Multi-level Acoustic Information](https://mlsanity.com/paper/2203.15326/) (2022)
- [ASVspoof 5: Design, Collection and Validation of Resources for Spoofing, Deepfake, and Adversarial Attack Detection Using Crowdsourced Speech](https://mlsanity.com/paper/2502.08857/) (2025)
- [Towards generalisable and calibrated synthetic speech detection with self-supervised representations](https://mlsanity.com/paper/2309.05384/) (2023)
- [SafeEar: Content Privacy-Preserving Audio Deepfake Detection](https://mlsanity.com/paper/2409.09272/) (2024)
- [Nes2Net: A Lightweight Nested Architecture for Foundation Model Driven Speech Anti-spoofing](https://mlsanity.com/paper/2504.05657/) (2025)
- [Speaker anonymization using orthogonal Householder neural network](https://mlsanity.com/paper/2305.18823/) (2023)
- [Attentive Merging of Hidden Embeddings from Pre-trained Speech Model for Anti-spoofing Detection](https://mlsanity.com/paper/2406.10283/) (2024)
- [Unmasking real-world audio deepfakes: A data-centric approach](https://mlsanity.com/paper/2506.09606/) (2025)
- [Spoofing-Aware Speaker Verification with Unsupervised Domain Adaptation](https://mlsanity.com/paper/2203.10992/) (2022)
- [Beyond Identity: A Generalizable Approach for Deepfake Audio Detection](https://mlsanity.com/paper/2505.06766/) (2025)
- [Towards the Next Frontier in Speech Representation Learning Using Disentanglement](https://mlsanity.com/paper/2407.02543/) (2024)

## Abstract (arXiv)

Audio deepfake detectors often fail to generalize across speakers, as they learn speaker-identity features rather than synthesis artifacts, known as implicit identity leakage. Existing methods address this but incur architectural complexity or training instability. This paper proposes a dual-granularity orthogonal disentanglement framework enforcing feature independence at two levels: sample-level cosine orthogonality captures directional decorrelation, while batch-level cross-covariance regularization eliminates linear correlations across embedding dimensions. A curriculum disentanglement schedule progressively strengthens the orthogonality constraint without auxiliary networks or adversarial dynamics. Experiments on ASVspoof 2019 LA, ASVspoof 2021 DF, and In-the-Wild datasets demonstrate that the proposed method achieves 1.35%, 7.88%, and 21.58% equal error rates (EER), respectively, surpassing gradient reversal disentanglement by 2.60% absolute on cross-dataset transfer.