# Attention-based Mixture of Experts for Robust Speech Deepfake Detection

arXiv: https://arxiv.org/abs/2509.17585 · HTML: https://mlsanity.com/paper/2509.17585/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal MoE models, one of 12 directions in Mixture-of-experts.
- Builds on 22 of its 34 references that are in the map.
- First posted on arXiv 22 Sep 2025.

## Placed in

- Mixture-of-experts / [Multimodal MoE models](https://mlsanity.com/moe/multimodal-moe-models/)

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [End-to-end anti-spoofing with RawNet2](https://mlsanity.com/paper/2011.01108/) (2020)
- [Does Audio Deepfake Detection Generalize?](https://mlsanity.com/paper/2203.16263/) (2022)
- [A Light CNN for Deep Face Representation with Noisy Labels](https://mlsanity.com/paper/1511.02683/) (2015)
- [ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild](https://mlsanity.com/paper/2210.02437/) (2022)
- [ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale](https://mlsanity.com/paper/2408.08739/) (2024)
- [Voice Conversion Challenge 2020: Intra-lingual semi-parallel and cross-lingual voice conversion](https://mlsanity.com/paper/2008.12527/) (2020)
- [The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methods](https://mlsanity.com/paper/1804.04262/) (2018)
- [RawBoost: A Raw Data Boosting and Augmentation Method applied to Automatic Speaker Verification Anti-Spoofing](https://mlsanity.com/paper/2111.04433/) (2021)
- [ADD 2023: the Second Audio Deepfake Detection Challenge](https://mlsanity.com/paper/2305.13774/) (2023)
- [MLAAD: The Multi-Language Audio Anti-Spoofing Dataset](https://mlsanity.com/paper/2401.09512/) (2024)
- [A Survey on Speech Deepfake Detection](https://mlsanity.com/paper/2404.13914/) (2024)
- [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)
- [Mixture of Experts Fusion for Fake Audio Detection Using Frozen wav2vec 2.0](https://mlsanity.com/paper/2409.11909/) (2024)
- [Leveraging Mixture of Experts for Improved Speech Deepfake Detection](https://mlsanity.com/paper/2409.16077/) (2024)
- [Post-training for Deepfake Speech Detection](https://mlsanity.com/paper/2506.21090/) (2025)
- [Unmasking real-world audio deepfakes: A data-centric approach](https://mlsanity.com/paper/2506.09606/) (2025)
- [DiffSSD: A Diffusion-Based Dataset For Speech Forensics](https://mlsanity.com/paper/2409.13049/) (2024)
- [Anomaly Detection and Localization for Speech Deepfakes via Feature Pyramid Matching](https://mlsanity.com/paper/2503.18032/) (2025)

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

- [From Self-Supervised Speech Models to Mixture-of-Experts for Robust Anti-Spoofing](https://mlsanity.com/paper/2606.14639/) (2026)
- [Explainable-by-Design Audio Deepfake Detection via Wiener-Hopf Linear Prediction](https://mlsanity.com/paper/2607.12584/) (2026)

## Abstract (arXiv)

AI-generated speech is becoming increasingly used in everyday life, powering virtual assistants, accessibility tools, and other applications. However, it is also being exploited for malicious purposes such as impersonation, misinformation, and biometric spoofing. As speech deepfakes become nearly indistinguishable from real human speech, the need for robust detection methods and effective countermeasures has become critically urgent. In this paper, we present the ISPL's submission to the SAFE challenge at IH&MMSec 2025, where our system ranked first across all tasks. Our solution introduces a novel approach to audio deepfake detection based on a Mixture of Experts architecture. The proposed system leverages multiple state-of-the-art detectors, combining their outputs through an attention-based gating network that dynamically weights each expert based on the input speech signal. In this design, each expert develops a specialized understanding of the shared training data by learning to capture different complementary aspects of the same input through inductive biases. Experimental results indicate that our method outperforms existing approaches across multiple datasets. We further evaluate and analyze the performance of our system in the SAFE challenge.