Anomaly Detection and Localization for Speech Deepfakes via Feature Pyramid Matching
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912289595064320 |
|---|---|
| author | Coletta, Emma Salvi, Davide Negroni, Viola Leonzio, Daniele Ugo Bestagini, Paolo |
| author_facet | Coletta, Emma Salvi, Davide Negroni, Viola Leonzio, Daniele Ugo Bestagini, Paolo |
| contents | The rise of AI-driven generative models has enabled the creation of highly realistic speech deepfakes - synthetic audio signals that can imitate target speakers' voices - raising critical security concerns. Existing methods for detecting speech deepfakes primarily rely on supervised learning, which suffers from two critical limitations: limited generalization to unseen synthesis techniques and a lack of explainability. In this paper, we address these issues by introducing a novel interpretable one-class detection framework, which reframes speech deepfake detection as an anomaly detection task. Our model is trained exclusively on real speech to characterize its distribution, enabling the classification of out-of-distribution samples as synthetically generated. Additionally, our framework produces interpretable anomaly maps during inference, highlighting anomalous regions across both time and frequency domains. This is done through a Student-Teacher Feature Pyramid Matching system, enhanced with Discrepancy Scaling to improve generalization capabilities across unseen data distributions. Extensive evaluations demonstrate the superior performance of our approach compared to the considered baselines, validating the effectiveness of framing speech deepfake detection as an anomaly detection problem. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_18032 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Anomaly Detection and Localization for Speech Deepfakes via Feature Pyramid Matching Coletta, Emma Salvi, Davide Negroni, Viola Leonzio, Daniele Ugo Bestagini, Paolo Sound Computer Vision and Pattern Recognition Multimedia The rise of AI-driven generative models has enabled the creation of highly realistic speech deepfakes - synthetic audio signals that can imitate target speakers' voices - raising critical security concerns. Existing methods for detecting speech deepfakes primarily rely on supervised learning, which suffers from two critical limitations: limited generalization to unseen synthesis techniques and a lack of explainability. In this paper, we address these issues by introducing a novel interpretable one-class detection framework, which reframes speech deepfake detection as an anomaly detection task. Our model is trained exclusively on real speech to characterize its distribution, enabling the classification of out-of-distribution samples as synthetically generated. Additionally, our framework produces interpretable anomaly maps during inference, highlighting anomalous regions across both time and frequency domains. This is done through a Student-Teacher Feature Pyramid Matching system, enhanced with Discrepancy Scaling to improve generalization capabilities across unseen data distributions. Extensive evaluations demonstrate the superior performance of our approach compared to the considered baselines, validating the effectiveness of framing speech deepfake detection as an anomaly detection problem. |
| title | Anomaly Detection and Localization for Speech Deepfakes via Feature Pyramid Matching |
| topic | Sound Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2503.18032 |