The paper introduces CaReCoS, a benchmark for multimodal reasoning over medical acoustic spectrograms, and evaluates the performance of vision and omni models, finding a maximum accuracy of 51.2%.

This study investigates the feasibility of pediatric asthma detection in emergency departments using breath sound recordings and machine learning with pretrained self-supervised speech representation…

This paper proposes a cyclic-prefix OFDM system for distributed acoustic sensing (DAS) to eliminate spatial inter-symbol interference and enable shared-waveform integrated sensing and communication.

This paper investigates neural activity during five auditory conditions using EEG recordings from a 5-year-old participant, revealing condition-specific modulation of neural oscillatory activity and d…

The paper proposes a causality-inspired multimodal Federated Domain Generalization framework to accurately classify respiratory sounds across different stethoscopes, overcoming the challenge of device…

A multimodal Mixture-of-Experts framework was developed for asthma detection using vocal biomarkers and clinical data, achieving better performance than unimodal and bimodal approaches.

This paper introduces CoughPhase-CLR, a self-supervised learning framework for cough representation learning using physiological phases, outperforming standard techniques on five downstream tasks.

A statistical model is proposed for UWB propagation channels inside the human chest for implant medical sensors, providing formulas for path loss, scattering, and channel impulse response.

This paper characterizes the gap between current DNN-based speech enhancement systems and hearing aid constraints, and proposes a lightweight architecture to meet these constraints.

The paper proposes a novel, highly secure real-time ECG monitoring framework that uses a patient's own ECG signal characteristics to generate unique, dynamic encryption keys, ensuring confidential dat…

This paper introduces a curated underwater audio dataset and proposes a margin-enhanced loss with feature alignment for underwater acoustic classification.

DSTAN-Med is a novel dual-channel attention framework that significantly improves False Data Injection (FDI) attack detection in IoMT medical devices by explicitly separating spatial and temporal depe…

Eight voice cloning models are benchmarked on five paralinguistic tasks, showing most preserve signal with modest degradation. Cloning English clinical speech into Japanese outperforms raw cross-lingu…

The paper designed a minimalist BCMI system to translate EEG-measured emotional valence into adaptive music, but preliminary testing showed that frontal alpha asymmetry was not reliably modulated by i…

The paper presents a lightweight on-device pipeline for converting paper ECGs into calibrated 12-lead signals and screening for Myocardial Infarction using SHAP for interpretability, achieving high ac…

This paper evaluates the use of EEG Foundation Models for burst suppression detection in ICU EEG data, achieving state-of-the-art performance.