arXiv:2606. 13952v2 Announce Type: replace-cross Abstract: Active Motor Noise Cancellation (AMNC) is a noise-reduction feature shipped in commercial fused deposition modeling (FDM) 3D printers.
arXiv:2606. 13952v1 Announce Type: cross Abstract: Active Motor Noise Cancellation (AMNC) ships in commercial fused deposition modeling (FDM) 3D printers as a hardware countermeasure against acoustic side-channel attacks that target intellectual property (IP).
The study audits the frequency and decoder‑depth claims of the audio jailbreak AdvWave‑P on the Qwen2‑Audio model. Using a protocol that masks frequency components in the short‑time Fourier transform domain, the authors evaluate attack success across 520 prompts, finding that 76.7% of adversarial inputs are labeled as jailbreaks. Detailed analyses show that masking specific frequency bands can sharply reduce attack success, with finer 16‑band partitions revealing that a narrow 7520‑7960 Hz band is critical, while global rescaling and re‑optimization experiments further illuminate the role of frequency partitioning and energy distribution in jailbreak effectiveness.
arXiv:2610.35272v1 Announce Type: cross Abstract: A transcriber listening through one microphone also hears everyone near it. We train causal voice isolators: masking transformers of 140M, 243M and 3...
EarLog is a real‑time, embedded system that opportunistically uses headphone playback as a probe to detect the acoustic reflex (AR), an involuntary ear response indicating protective activation during high‑load listening. By employing content‑conditioned residual sensing, a resonance‑constrained sparse FIR model, and dual‑microphone observations, EarLog suppresses noise from nonstationary content, individual ear acoustics, and device variations to identify weak AR signals. In a study with 81 participants, 16 headphone models, and over 400 hours of recordings, EarLog achieved 99.0% sensitivity and 98.7% specificity against a clinically referenced benchmark, enabling continuous, listener‑specific AR monitoring during everyday listening.
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.
The study explores whether AI‑generated impulsive sounds can be distinguished from real sounds using group delay analysis. It finds that while onset‑region group‑delay distributions are nearly identical, the decay‑region shows a significant divergence (KL = 0.322 vs. 0.022). Various classifiers—single‑feature AUC ≈ 0.720, Random Forest AUC ≈ 0.884, and CNN/transformer models achieving up to 94% accuracy—demonstrate that decay‑region group delay provides strong discriminative power, with Random Forest remaining stable across different STFT settings.
arXiv:2609.23340v1 Announce Type: cross Abstract: Pitch estimation on an edge device is constrained in three ways at once. The model must be small, it must stay accurate when the input is noisy, and...
arXiv:2610.09819v1 Announce Type: cross Abstract: Acoustic foundation models (AFMs) have democratized acoustic applications, enabling powerful models for tasks ranging from speech recognition to spea...
arXiv:2606. 14658v1 Announce Type: cross Abstract: Artificial Intelligence (AI) is increasingly used to automate a variety of real-world computer vision (CV) applications, such as autonomous vehicle control, facial recognition, and security cameras.
The paper investigates how to evaluate audio‑language models by separating the use of acoustic evidence from the need to invoke a generative audio model. Using a controlled call‑decision framework, the authors compare policies that rely on transcript labels, encoder outputs from CLAP, AST, or WavLM, and optional calls to generative models such as Qwen2‑Audio, Qwen2.5‑Omni, or MOSS‑Audio. Results on the VocalSound dataset show that while transcript‑only accuracy is low (0.296), encoder‑only controls achieve high accuracy (≈0.85) without any generative calls, and adding generative calls yields only a marginal improvement (0.925 vs. 0.921).
The paper investigates how large audio‑language models (LALMs) hallucinate objects by affirming sounds that are not present. Using a black‑box causal test, the authors isolate and remove the claimed evidence region via spectral gating and compare the effect against a random‑window control across a 2×2×2 grid on three LALMs. The study finds that localization of evidence improves detection over random removal, that raw detection values are model‑dependent, and that contrastive decoding combining blank and language‑prior contrasts can significantly boost accuracy, but a unified causal‑grounding profile does not transfer between models.
The paper investigates how to evaluate generative audio large language models (Audio‑LLMs) on known closed‑set tasks by separating the decision to call a generative model from the use of acoustic evidence. It introduces a controlled call‑decision framework where a policy can choose between a transcript label, encoder evidence from CLAP, AST, or WavLM, or a generative call to Qwen2‑Audio, Qwen2.5‑Omni, or MOSS‑Audio, and measures the impact of generative calls on accuracy. Results on the VocalSound dataset show that while transcript‑only accuracy is low (0.296), encoder‑based controls achieve high accuracy (≈0.85) without any generative calls, and adding generative calls yields only a marginal improvement (0.925 vs. 0.921).