325 papers
This paper derives accurate analytical expressions for the matched-filter SNR distribution of one-dimensional continuous aperture arrays in correlated Rayleigh fading environments using a truncated hypoexponential model, demonstrating significantly improved accuracy over standard gamma approximations and superior performance compared to discrete antenna arrays.
ReDimNet2 introduces an improved speaker verification architecture that incorporates time-pooled dimension reshaping to enable aggressive channel scaling with minimal computational overhead, achieving superior accuracy-efficiency trade-offs across a family of seven model configurations on VoxCeleb1 benchmarks.
This study demonstrates that acoustic-to-articulatory inversion models trained on denoised MRI data can effectively reconstruct vocal tract shapes from clean speech, achieving performance comparable to MRI-based methods with an RMSE of 1.56 mm.
This paper presents a comparative study demonstrating that incorporating manually corrected phonetic segmentation into speech-based vocal tract reconstruction models yields performance approaching the MFCC baseline, outperforming uncorrected or automatically aligned phonetic representations.
This study demonstrates that while centralized learning yields the highest accuracy in classifying third molar and mandibular canal overlap on panoramic radiographs, federated learning serves as a superior privacy-preserving alternative that significantly outperforms local learning models.
This paper demonstrates that image-in-image steganography schemes are highly detectable because their embedding process creates a mixing pattern identifiable via independent component analysis, allowing a simple method based on the first four moments of wavelet-decomposed components to achieve up to 84.6% accuracy, while keyless extraction networks and classical steganalysis methods like SRM achieve even higher detection rates.
This paper presents a comprehensive taxonomy and systematic review of Silent Speech Interfaces, highlighting their evolution from traditional signal processing to LLM-driven semantic alignment that overcomes biosignal sparsity, enabling robust, privacy-preserving, and wearable-ready human-computer interaction.
This paper explores the potential of flexible intelligent metasurfaces (FIMs) as a transformative technology for next-generation wireless networks by detailing their hardware architectures, application scenarios, and performance advantages over rigid arrays, while also addressing key challenges and future research directions.
This paper proposes a probabilistic forecasting framework using clustered quantile regression on UK low-voltage transformer data to dynamically optimize thermal protection settings, achieving a 10–12% capacity increase while enabling risk-informed operational decisions through direct overheating risk quantification.
This paper proposes a complex-valued end-to-end deep learning framework that eliminates the digital precoder via KKT conditions to enable stable, efficient hybrid beamforming for both far-field and near-field XL-MIMO systems, offering robust performance in both indirect (CSI-based) and direct (pilot-based) modes while significantly reducing complexity and improving spectral efficiency over existing methods.
This paper proposes an emergency-aware and frequency-constrained HVDC planning method for multi-area asynchronously interconnected grids that integrates a coordinated emergency control scheme and an enhanced system frequency response model to optimize inter-area HVDC capacities while balancing economic efficiency with frequency security requirements.
This paper proposes a paralinguistic-enhanced fine-tuning (PE-FT) protocol, which utilizes layer-wise analysis to implement selective-layer fine-tuning and an auxiliary dual-level classification head, effectively equipping Large Audio Language Models with the ability to interpret paralinguistic cues and outperforming traditional all-layer fine-tuning strategies.
This paper proposes a deep-learning-based interference-aware multiuser beam training framework (DL-IABT) for near-field XL-MIMO systems that directly predicts analog beam indices from limited uplink sensing measurements to achieve near-optimal sum-rate performance while significantly reducing pilot overhead.
This paper proposes a robust parametric model predictive control framework for microgrid dispatch that addresses the endogenous uncertainty of battery degradation by integrating an XGBoost-based probabilistic degradation model with tunable penalty weights to optimize the trade-off between operational costs and long-term battery health under varying temperature conditions.
This paper investigates the impact of array geometry on axial sidelobe interference in near-field multi-user MIMO systems, deriving closed-form gain expressions to demonstrate that uniform planar arrays outperform other configurations by achieving the lowest sidelobe levels and highest sum rates.
This paper proposes a joint source-channel coding and resource allocation framework for LEO satellite-based Earth observation missions that minimizes transmit power under quality-of-service constraints by approximating the complex relationship between compression, signal quality, and image reconstruction through a curve-fitting model and a dedicated optimization algorithm.
This paper introduces Dr. SHAP-AV, a Shapley value-based framework that reveals audio-visual speech recognition models exhibit a persistent audio bias and dynamically shift toward visual reliance under noise, providing critical insights for developing robust modality-weighting mechanisms.
This paper presents a control framework for a morphing-wing drone that enables it to traverse gaps narrower than its wingspan by dynamically sweeping its wings mid-flight, utilizing an aerodynamic model and nonlinear model predictive control to manage lift loss and ensure precise trajectory tracking.
This paper addresses the critical need for accessible validation data in Structural Health Monitoring by introducing an open-source, simulated dataset of a fixed-fixed steel beam that incorporates realistic environmental variations, damage scenarios, and sensor faults to facilitate the development and verification of novel data-driven and hybrid SHM strategies.
This paper proposes a decentralized cooperative localization framework for multi-robot systems in GPS-denied environments that utilizes asynchronous sensor fusion, automatic coordinate alignment, and a dual-landmark evaluation strategy to achieve significantly higher accuracy and robustness compared to centralized methods.