arXiv Machine Learning September 3, 2026 By S. Sutharya, Remya K. Sasi

Half-Truth Audio Detection and Localisation: A Lightweight Cross-Attentive Architecture and a Cross-Corpus Diagnostic Study

Read the original on arXiv Machine Learning →

The paper introduces CAFNet, a lightweight cross‑attentive neural network that fuses MFCC, LFCC, and Chroma‑STFT features to detect and localise partially manipulated (half‑truth) speech. CAFNet achieves high ternary accuracy (97.55%) and low boundary mean absolute error (0.037 s) on the MLADDC benchmark, while demonstrating that cross‑corpus transfer depends on both capability and corpus characteristics. Ablation studies show that cross‑attention fusion is the most critical component, and removing a deeply supervised auxiliary head improves in‑domain performance and reduces variance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

benchmarks

arXiv Machine Learning

Aug 17

Trajectory Dynamics in Self-Supervised Learning Latent Space for Audio Deepfake Detection

arXiv:2608. 13817v1 Announce Type: cross Abstract: Human speech production is constrained by physiology, giving rise to characteristic temporal structure on acoustic signals.

By Tom\'as Andrade Weber

diffusion benchmarks

arXiv AI

Aug 17

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 Machine Learning

Jul 27

Probing Speaker Identity Sensitivity in Audio Deepfake Detectors

arXiv:2607. 21820v1 Announce Type: cross Abstract: Audio deepfake detectors are trained to distinguish genuine speech from synthetic speech and often perform well on standard benchmarks.

By Daniyal Kabir Dar, Arun Ross

robotics benchmarks

arXiv Computation and Language

Sep 24

Lost in Speech: Trilingual Spoken Hallucination Detection Across Audio and Transcripts

The paper introduces a trilingual spoken hallucination detection benchmark covering English, Russian, and Kazakh news, with 12,013 samples that include synthetic alterations and severity levels, as well as 290 fact‑checked misinformation items. Detectors are evaluated in a reference‑free setting on text, ASR transcripts, and audio, revealing that most models underperform baseline classifiers, except Gemma‑3n on transcripts. Synthetic‑trained detectors achieve high macro‑F1 scores on real‑world misinformation, but Russian provenance analysis highlights model‑dependent signals that confound synthetic benchmarks.

By Meruyert Aristombayeva, Jason S. Lucas, Chaewan Chun, Dongwon Lee

fine-tuning multimodal benchmarks safety

arXiv AI

Jul 29

Less is More: Modality-Decoupling for General AIGC Audio-Video Detection

arXiv:2607. 25543v1 Announce Type: cross Abstract: Generative AI has rapidly expanded audio-visual forgery beyond human-centric deepfakes into general scenes.

By Jielun Peng, Yabin Wang, Yaqi Li, Jincheng Liu, Xiaopeng Hong, Athanasios V. Vasilakos

multimodal

Hugging Face Trending Papers

Aug 12

Confucius4-TTS: Transcript-Free Cross-Lingual Zero-Shot TTS with a Learnable Speaker Encoder

Recent advances in zero-shot text-to-speech (TTS) have substantially improved speech quality and voice cloning fidelity. However, many zero-shot TTS systems still depend on audio prompt transcripts at inference time.

llms multimodal benchmarks