arXiv:2607. 26472v1 Announce Type: cross Abstract: Audio deepfake detectors often degrade when generators, corpora, or recording conditions change.
Audio deepfake detectors often degrade when generators, corpora, or recording conditions change. We use a Diffusion Transformer (DiT), trained only on bona fide speech, as a frozen reconstruction probe.
arXiv:2609.08899v2 Announce Type: replace-cross Abstract: Speech deepfakes can mimic a speaker's voice convincingly enough to deceive listeners and automated systems. This has driven strong progress...
arXiv:2511. 21325v2 Announce Type: replace-cross Abstract: Deepfake (DF) audio detectors still struggle to generalize to out of distribution inputs.
The paper introduces NEUROTOKEN, a unified neural network for auditory attention decoding (AAD) that jointly predicts the attended speaker’s direction and source by modeling the conditional likelihood of the attended envelope given EEG. It employs a conditional flow‑matching head (ATTUNEFLOW) and two inference‑time ensembles (QUADTRACK and ENV‑FLOW) to improve source‑AAD accuracy and reduce variance across subjects. Experiments on KU Leuven, DTU, and NJU datasets show significant gains over existing baselines and reveal that prior direction‑AAD results overestimate performance under stricter protocols.
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.
arXiv:2609.13842v1 Announce Type: cross Abstract: Recent advances in speech synthesis and voice conversion have made deepfake speech increasingly realistic, making generalization to unseen spoofing a...
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.
arXiv:2606. 10223v1 Announce Type: cross Abstract: Attributing a synthetic utterance to its originating system remains an open challenge: closed-set models fail to reject unseen synthesizers and produce overconfident predictions.
arXiv:2508. 07048v2 Announce Type: replace-cross Abstract: Autoregressive (AR) encoder-decoder models dominate high-quality multilingual ASR, but their left-to-right decoders make inference latency scale with transcript length.
The paper introduces CUES, a lightweight heuristic for selecting encoder combinations in large audio‑language models by estimating complementarity through Pearson correlations of single‑encoder performance profiles. Using a frozen SmolLM2‑135M backbone, CUES consistently identifies optimal encoder sets for each track on the XARES‑LLM benchmark without requiring fusion training or test data. On broad audio tasks, CUES selects a diverse trio of encoders, improving performance by 4.3% over Whisper‑medium, while on text generation it opts for a focused speech‑only pair, outperforming mHuBERT‑147 by 6.3%. The results illustrate how correlation signals guide a diversity–interference trade‑off across different task families.
The study evaluates audio provenance attribution systems, showing that high clean‑benchmark accuracy does not translate to robustness after codec compression. Using a prospectively registered protocol, the authors measured closed‑set attribution performance on two corpora after single‑stage codec transport, finding significant degradation—up to 70.3 Macro‑F1 points for WavLM‑Base+ and 61.0 for W2V2‑BERT 2.0—depending on codec settings and representation. The results demonstrate that clean accuracy alone cannot guarantee deployment robustness across different codecs and representations.
arXiv:2609.23830v1 Announce Type: new Abstract: Comparing audio-visual deepfake detectors requires coordinating dataset adaptation, temporal input representation, model interfaces and experimental co...