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: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:2606. 19579v1 Announce Type: cross Abstract: Audio deepfakes generated by neural text-to-speech and voice-cloning systems threaten speaker verification and public discourse at scale.
UniAE-MoE is a unified audio encoder that uses a Mixture-of-Experts architecture to model cross‑domain audio representations. It integrates encoder components from Qwen2‑Audio and Audio‑Flamingo 3, enhances them with SwiGLU and shared experts, and applies a two‑stage instruction‑tuning strategy along with task‑specific data scaling. The model achieves state‑of‑the‑art results on the XARES‑LLM benchmark (0.802) and tops the Interspeech 2026 Audio Encoder Capability Challenge, demonstrating strong generalization across speech, music, and general audio tasks.
arXiv:2607. 04848v1 Announce Type: cross Abstract: While audio deepfake detection has advanced significantly, representative detectors show limited generalization to synthetic sound effects.
arXiv:2607. 00247v1 Announce Type: cross Abstract: Large audio-language models (LALMs) frequently hallucinate by overriding acoustic evidence with language priors.
arXiv:2604. 01832v1 Announce Type: cross Abstract: We introduce GAP-URGENet, a generative-predictive fusion framework developed for Track 1 of the ICASSP 2026 URGENT Challenge.
arXiv:2607. 03134v1 Announce Type: cross Abstract: Recent research expands beyond binary anti-spoofing with the emergence of Source Tracing, the task of identifying the specific generative origins of synthetic speech.
arXiv:2601. 09239v5 Announce Type: replace-cross Abstract: Speech tokenizers are a key building block of fully discrete Speech LLMs.
arXiv:2606. 30700v1 Announce Type: cross Abstract: Self-supervised learning enables audio representations that transfer across domains and tasks.
arXiv:2608. 13817v1 Announce Type: cross Abstract: Human speech production is constrained by physiology, giving rise to characteristic temporal structure on acoustic signals.
arXiv:2607. 02119v1 Announce Type: cross Abstract: While Large Multimodal Models excel in comprehension, high-throughput inference engines lack native support for multimodal generation.
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.