The paper introduces an active noise cancellation (ANC) system designed for open‑ear wearables such as smart glasses and VR headsets, eliminating the need for an in‑ear error microphone. Using eight microphones around the frame and a neural network to predict ear‑level noise, the system generates real‑time anti‑noise signals. In tests with eleven users and eight environments, it achieved a mean noise reduction of 9.6 dB without calibration and 11.2 dB with brief calibration, and the approach generalizes to other open‑ear devices.
By Kuang Yuan, Freddy Yifei Liu, Tong Xiao, Yiwen Song, Chengyi Shen, Saksham Bhutani, Justin Chan, Swarun Kumar
The paper introduces SpectrumAudit, a label‑sealed auditing method for wearable human‑activity recognition models that uses phase‑randomized full‑window stimuli to probe sensor biases. By replaying the DC component and a zero‑mean residual on held‑out subjects, the audit demonstrates significant accuracy drops across 27 victim models, with DC perturbations proving more harmful than AC in most cases. The study also shows that the audit can distinguish between persistent sensor offsets and zero‑mean variations under a fixed peak‑budget.
By Qingyu Wu, Yuan Wei, Renju Liu, Hua Cheng
arXiv:2603. 02794v2 Announce Type: replace-cross Abstract: We present TVF (Time-Varying Filtering), an interpretable, low-latency speech enhancement model for real-time, on-device assistive hearing.
By Riccardo Rota, Kiril Ratmanski, Jozef Coldenhoff, Milos Cernak
arXiv:2606. 04103v1 Announce Type: cross Abstract: Conventional hearing aids rely on fixed, frequency-dependent amplification and compression to manage reduced sensitivity, which often fails to provide sufficient listening support in complex environments, such as situations with multiple speakers (the ``cocktail party'' problem).
By Alejandro Ballesta Rosen, Jason Mikiel-Hunter, Julian Maclaren, Jack Collins, Richard F. Lyon, Simon Carlile
CoarseSoundNet is a deep learning framework designed to classify ecological soundscapes into biophony, geophony, and anthropophony under realistic passive acoustic monitoring conditions. The study systematically explores model architectures, training data composition, and evaluation strategies, finding that adding more domain‑similar data, a silence class, and post‑hoc calibration improves performance. An ecological case study shows that pre‑filtering recordings with CoarseSoundNet produces acoustic index trends similar to ground‑truth filtering, though the impact on avian alpha‑diversity relationships is modest.
By Alexander Gebhard, Andreas Triantafyllopoulos, Dominik Arend, Sandra M\"uller, Svenja Schmidt, Michael Scherer-Lorenzen, Bj\"orn W. Schuller
The paper introduces a simulation-based method for detecting a user's own voice in hearing aids using only a single microphone. It employs a data augmentation strategy with simulated acoustic transfer functions to train a transformer classifier, achieving over 90% accuracy on both simulated and real-world recordings. The approach reduces hardware complexity and power consumption while maintaining robust performance across varied spatial conditions.
By Mathuranathan Mayuravaani, W. Bastiaan Kleijn, Andrew Lensen, Charlotte S{\o}rensen
arXiv:2608. 05697v1 Announce Type: cross Abstract: Respiration provides a continuously available window into physiological state and behavior.
By Mohammad Hosseini, Hamed Khatounabadi, Mohammad Fakharzadeh
arXiv:2605. 00865v2 Announce Type: replace-cross Abstract: We tested whether auditory-evoked EEG supports subject-independent five-vowel perception decoding when trial identity, model identity, prediction provenance, and participant-level inference are controlled within a single benchmark.
By Xiaoyang Li, Zeyan Tao
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.
By Ali Alavi, Donald S. Williamson
The paper introduces SAC‑Bench, a benchmark of 616,031 audio clips that test audio‑language models (ALMs) on how they handle conflicts between spoken claims and acoustic evidence. It covers 188 sound‑event classes across seven semantic, temporal, and spatial tasks, pairing environmental recordings with either compatible or contradictory synthesized spoken claims and including audio‑only controls. Evaluation of five open‑weight ALMs shows that high audio‑only accuracy often coexists with significant drops in performance under conflicting claims, revealing gaps in conflict robustness and the mixed effects of prompt interventions.
By Wenbin Wang, Yuheng Li, Koichiro Yoshino
The paper introduces a multi‑party backchannel prediction benchmark built from the AMI meeting corpus, featuring 682 masked‑listener views, 190 speakers, and 18,697 backchannel events. A state‑of‑the‑art dyadic model performs at chance when applied zero‑shot to meetings, but its frozen acoustic features are still informative, and retraining improves performance to an AUROC of 0.751. The study reveals that listener conditioning helps only for listeners seen during training, that speaker identity is entangled with useful cues, and that backchannel rates vary significantly across individuals, prompting the authors to report both AUROC and event‑F1 metrics.
whyItMatters":"The benchmark and evaluation tools provide a standardized, person‑disjoint testbed for advancing multi‑party backchannel prediction research."
By Mohammed Hafsati, Ahmed Loughzali
The paper introduces RALCT, a lightweight Convolutional Transformer that combines randomized audio augmentations, MFCCs, and log‑mel spectrograms to extract robust features for environmental sound recognition. With only about 310,000 parameters, RALCT achieves state‑of‑the‑art accuracy—over 93% on UrbanSound8K, peaking at 94.56%—making it suitable for deployment on mobile devices. The authors also develop a mobile app that integrates the model to provide real‑time safety alerts for hearing‑impaired users.
By Julia Huang