arXiv Machine Learning June 9, 2026 By Weichuang Shao, Iman Yi Liao, Tomas Henrique Bode Maul, Tissa Chandesa

DHAuDS: A Dynamic and Heterogeneous Audio Benchmark for Test-Time Adaptation

Read the original on arXiv Machine Learning →

arXiv:2511. 18421v2 Announce Type: replace-cross Abstract: Existing Test-time Adaptation (TTA) studies rely heavily on static and homogeneous corruption protocols, such as ImageNet-C and CIFAR-10-C/100-C, leading to inconsistent evaluation settings and potentially inflated robustness estimates that are compared with real-world situations.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

benchmarks

arXiv AI

Jul 7

Measuring the Robustness of Audio Deepfake Detection under Real-World Corruption

arXiv:2503. 17577v2 Announce Type: replace-cross Abstract: Deepfakes have emerged as a widespread and rapidly escalating concern in generative AI, spanning images, audio, and videos.

By Xiang Li, Pin-Yu Chen, Wenqi Wei

benchmarks

arXiv AI

2d ago

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.

By Wan Lin, Li Wang, Jindong Wang, Kunyu Feng, Zhizheng Wu

benchmarks

arXiv AI

Jul 21

Time-Frequency Consistency Learning for Robust Speech Deepfake Detection

arXiv:2607. 17761v1 Announce Type: cross Abstract: Recently, speech deepfake detection (SDD) has achieved significant progress.

By Jun Xue, Zhuolin Yi, Yanzhen Ren, Yihuan Huang, Jiayu Xiong, Yi Chai, Guanxiang Feng, Jiajun Liu, Tong Zhang

benchmarks safety

arXiv Machine Learning

Jul 7

An Intervention-Based Framework for Shortcut Diagnosis in Spoofing Countermeasures

arXiv:2607. 03150v1 Announce Type: cross Abstract: While deepfake audio detection systems achieve high performance in controlled benchmarks, their reliability often diminishes in the wild.

By Santiago Rubio, Pilar Bello, Dayana Ribas, Antonio Miguel, Eduardo Lleida, Alfonso Ortega

benchmarks

arXiv AI

Jul 14

VoxENES 2026: Benchmarking Generalization of Speech Spoofing Detectors Against LLM-Era TTS and Voice Conversion

arXiv:2607. 11706v1 Announce Type: cross Abstract: Modern LLM-driven text-to-speech (TTS) and voice conversion (VC) systems produce synthetic speech that differs from the generators represented in many legacy spoofing benchmarks.

By Aastha Sharma, Guangjing Wang

llms fine-tuning multimodal benchmarks

arXiv AI

1d ago

Distinguishing AI-Generated Music from Edited Audio as a Hard-Negative Robustness Task

arXiv:2608. 14916v1 Announce Type: cross Abstract: AI-generated music detectors are commonly evaluated against original songs, but real-world uploads are often remixed, re-encoded, pitch-shifted, or otherwise edited.

By Alexandru-Stefan Morosanu, Valerian Cecan, Stefan-Daniel Achirei, Laura Erhan

llms

Related stories

Measuring the Robustness of Audio Deepfake Detection under Real-World Corruption

Teffic-Audio: Tell Fact from Fiction

Time-Frequency Consistency Learning for Robust Speech Deepfake Detection

An Intervention-Based Framework for Shortcut Diagnosis in Spoofing Countermeasures

VoxENES 2026: Benchmarking Generalization of Speech Spoofing Detectors Against LLM-Era TTS and Voice Conversion

Distinguishing AI-Generated Music from Edited Audio as a Hard-Negative Robustness Task