analiza aiqbench
Teffic-Audio introduces a robust speech deepfake detection framework that prioritizes generalization across heterogeneous spoofing mechanisms through advanced training recipes rather than architectural complexity. By leveraging open-source data with balanced sampling and diverse augmentation, the system achieves state-of-the-art error rates on the Speech-DF-Arena benchmark while maintaining an efficient performance-complexity trade-off. This work advances practical defenses against evolving voice synthesis threats without relying on proprietary datasets or excessive model size.
Teffic-Audio: Tell Fact from Fiction
arXiv:2607.28351v2 Announce Type: replace-cross Abstract: Speech deepfake detection has expanded in scope with increasingly heterogeneous spoofing mechanisms, including speech synthesis, voice conversion, vocoder reconstruction, and neural-codec resynthesis. The resulting spoofing artifacts can be further shaped by variability in source speech, recording environments, and transmission channels. This variability makes robust generalization across heterogeneous conditions a central requirement for practical detection systems. This report presents Teffic-Audio, a general speech deepfake detection system designed for comprehensive evaluation environment. Teffic-Audio adopts a straightforward detector architecture consisting of a Conformer-based speech encoder, multi-head attentive statistics pooling, and a binary classifier. Rather than relying on additional architectural complexity, the system improves generalization through its training recipe, which integrates multi-source data, attack- and source-balanced sampling, and diverse audio augmentation. Trained only with open-source data, Teffic-Audio achieves a pooled EER of 1.454% on the 14 test sets of Speech-DF-Arena, outperforming all currently public systems on the leaderboard. It also obtains the lowest EER on five individual test sets and shows a favorable performance-complexity trade-off compared with larger leading systems. Overall, Teffic-Audio provides a strong and practical reference system for general speech deepfake detection.
Abstract:Speech deepfake detection has expanded in scope with increasingly heterogeneous spoofing mechanisms, including speech synthesis, voice conversion, vocoder reconstruction, and neural-codec resynthesis. The resulting spoofing artifacts can be further shaped by variability in source speech, recording environments, and transmission channels. This variability makes robust generalization across heterogeneous conditions a central requirement for practical detection systems. This report presents Teffic-Audio, a general speech deepfake detection system designed for comprehensive evaluation environment. Teffic-Audio adopts a straightforward detector architecture consisting of a Conformer-based speech encoder, multi-head attentive statistics pooling, and a binary classifier. Rather than relying on additional architectural complexity, the system improves generalization through its training recipe, which integrates multi-source data, attack- and source-balanced sampling, and diverse audio augmentation. Trained only with open-source data, Teffic-Audio achieves a pooled EER of 1.454% on the 14 test sets of Speech-DF-Arena, outperforming all currently public systems on the leaderboard. It also obtains the lowest EER on five individual test sets and shows a favorable performance-complexity trade-off compared with larger leading systems. Overall, Teffic-Audio provides a strong and practical reference system for general speech deepfake detection.
16 pages, 1 figure, 7 tables. Technical report. Project page: this https URL
Sound (cs.SD); Artificial Intelligence (cs.AI)
arXiv:2607.28351 [cs.SD]
(or arXiv:2607.28351v2 [cs.SD] for this version)
https://doi.org/10.48550/arXiv.2607.28351 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 287 cuvinte
Subiecte conexe
Can John Ternus find Apple’s next big thing?
The Verge · 21 sept. 2026
A Candid Abacus AI Review: The All-in-One AI Platform for Professionals & Enterprises
KDnuggets · 10 sept. 2026
How Sonos rebooted itself
The Verge · 3 sept. 2026
If This Were a Test, How Much Would It Cost?
LessWrong · 16 iun. 2026