Papers

The study of Target Speaker Extraction (TSE) aims to isolate a desired speaker from overlapping speech mixture given auxiliary cues. Existing systems are typically designed for specific cue types, limiting flexibility when cue availability varies across scenarios. We present WeSep, a unified framework that reformulates TSE as a heterogeneous cue-conditioned learning problem. In WeSep, cue modules and separator backbones are decoupled through standardized interfaces, enabling configurable cue injection and flexible integration of diverse modalities. The design enables systematic study of cue structure, intra- and cross-modal interaction, and dynamic cue availability within a shared optimization framework, facilitating adaptation to real-world conditions. Experiments across enrollment, spatial, visual, and textual cues reveal modality-dependent characteristics and demonstrate stable optimization under heterogeneous cue availability. The toolkit will be publicly available.

We present a novel calculus of variations (CoV)-based framework for the characterizing of, and beamforming over, continuous electromagnetic manifolds of arbitrary multiple-input multiple-output (MIMO) array geometries. Building upon the discrete moment-matrix formulation of the state-of-the-art (SotA), the proposed framework simultaneously overcomes three of its fundamental limitations: (i) the point-source approximation error incurred by the near-field radiation operator; (ii) the confinement of the beamforming space to the N-dimensional subspace dictated by the hardware port count; and (iii) the generalization to arbitrary array geometries. To this end, each mesh element is modeled as a two-dimensional planar patch whose spatially averaged Green's function is evaluated via Gauss-Legendre (GL) quadrature, yielding a strictly more accurate near-field representation at negligible additional cost, while a continuous feeding function w(p) in L^2(S_T), introduced as the infinite-dimensional limit of the N-port network, lifts the optimization onto a hardware-decoupled current subspace of dimension K >> N. As an application example, we employ the proposed CoV-based framework to derive closed-form optimal beamformers for both unconstrained field-strength maximization, and a near-field pattern synthesis under a power density (PD) and region constraints, establishing their exact analogy to the discrete and generalized matched filters. Full-wave MATLAB Antenna Toolbox validation confirms consistent near-field accuracy gains over the SotA baseline for both linear and planar geometries at comparable computational cost.

Machine learning methods are increasingly used for traffic prediction in applications such as autonomous driving. Such predictions must be both highly accurate and immediately available, making methods with low computational costs and fast training times of interest. One such method is reservoir computing, in which the rich dynamics of a nonlinear system serves as a computational substrate and only a linear readout vector is trained. In this work we use a traffic network as the reservoir for predicting the behavior of an undersensed traffic network. This matching of the highly nonlinear dynamics allows for similar encoding between the behaviors of the reservoir and target network, enabling a more direct prediction. We show that a reservoir governed by the Improved Intelligent Driver Model (IIDM) satisfies the echo state property for a class of slowly-varying inputs. Through simulations we show that the echo state property likely holds for a larger class of inputs, and that the IIDM reservoir computer (IIDM-RC) accurately predicts an undersensed vehicle network governed by varying car-following models. We also compare with echo state networks (ESNs) and Long Short-Term Memory (LSTM) networks, finding improvements using IIDM-RC in both prediction accuracy and training time.

Cross-modal knowledge distillation can transfer diagnostic knowledge from a strong but costly teacher modality to a cheaper and more deployable student modality. In medical image analysis, however, the two modalities are often unpaired: they are collected from different patient cohorts and occupy geometrically incompatible feature spaces. This makes instance-level distillation invalid and direct feature matching unreliable. To address these challenges, we propose Shared Semantic Codebook Distillation (SSCD), which compares teacher and student representations through a shared discrete codebook. Each image is represented as a distribution over a common, modality-agnostic vocabulary, and knowledge is transferred by aligning these distributions across modalities, both globally and class-conditionally, without requiring paired samples or directly comparable raw features. The codebook is evolved online by exponential moving average and kept diverse through entropy regularization and dead-code restart. At inference, all teacher-side and codebook modules are discarded, leaving only the student encoder and classifier. On two heterogeneous unpaired settings, OCT-to-fundus retinal disease classification and CT-to-chest-X-ray pneumonia classification, SSCD improves the student from 64.5 to 70.2 macro-F1 and from 73.8 to 76.3 macro-F1, respectively, outperforming all evaluated distillation baselines on both settings. Code and pretrained models are available at https://github.com/DillanImans/SSCD-unpaired-distillation

Automated classification of pulmonary disease from chest radiographs is a widely studied application of machine learning in medical imaging. This paper presents a pilot study evaluating classical texture- and gradient-based feature representations for distinguishing COVID-19 from other forms of pneumonia using the publicly available COVID-19 Image Data Collection (668 posteroanterior/anteroposterior radiographs from 408 patients). Using histogram of oriented gradients (HOG) and gray-level co-occurrence matrix (GLCM) texture descriptors with classical classifiers (logistic regression, random forest, and support vector machine), evaluated under patient-level 5-fold stratified cross-validation to prevent data leakage, we obtain a best mean accuracy of 75.4% and AUC of 0.755, modestly exceeding the 71.6% majority-class baseline. We report these results transparently, including their limitations, and use them to motivate and scope a proposed multi-modal deep learning architecture – combining convolutional and transformer-based encoders across imaging modalities – as a direction for future work requiring access to larger, multi-institutional, ethically sourced datasets.

We propose a statistical methodology that quantifies the similarity of typefaces between printed historical books. This provides a tool that accelerates philological analysis. Using character prototypes derived from clustering and aligning automatically extracted character images, the method defines a typeface distance between any two books. To produce actionable outputs, we develop an a contrario statistical framework to interpret the significance of the computed typeface distances. We apply the method to the philological study of 17 th -century Spanish printed theatre chapbooks in a quantity that exceeds the capabilities of systematic visual inspection by human experts. Our method enables the automatic comparison of Roman and Italic types extracted from different books. After validation by human experts, our method has led to new printer attributions being discovered, and former printer attributions being revised. This success strongly suggests that our method has the potential to enable digital bibliography on a larger scale than was previously possible.

It is known that cooperative systems, and more generally systems monotone with respect to cones, behave under appropriate irreducibility conditions like one-dimensional systems, as evidenced by results such as Hirsch's generic convergence theorem. It is also known, following work of Sanchez and others, that two-cooperative systems, those preserving a generally nonconvex 2-dimensional cone (tested through the diminishing of sign variations), behave like two-dimensional systems, as evidenced by Poincare–Bendixson-type theorems. In these notes I attempt to give some geometric intuition for these dimensionality reductions, based on Birkhoff–Hilbert contractions of the projective metric on a positive cone.

Space object tracking poses challenging estimation problems due to the significantly non-Gaussian distributions that can arise, particularly under highly nonlinear dynamics or during periods of measurement unavailability. Adaptive Gaussian mixture filters can dynamically adjust their mixture resolution to systematically approximate these non-Gaussian distributions, but challenging estimation problems can still produce highly uncertain or inaccurate estimates, especially during prolonged observation gaps. Smoothing algorithms can significantly improve filtered estimates by incorporating future measurement information for applications where immediacy is not required, but smoothing in nonlinear, non-Gaussian settings poses additional theoretical and computational challenges. This work develops a new recursive Bayesian smoothing algorithm for nonlinear systems that refines Gaussian mixture posteriors produced by a forward adaptive Gaussian mixture filter. A two-filter smoothing approach approximates the future measurement information by an information-form Gaussian mixture in the state variable. Techniques from nonlinear Gaussian mixture filtering including splitting, merging, and recursive measurement updating are also incorporated to improve the accuracy and computational efficiency of this approximation. The proposed smoother's estimation capabilities are demonstrated on space object tracking problems for Molniya and Earth-Moon halo orbits and shown to significantly reduce estimation error and uncertainty compared to the forward filter.

This paper presents the North Carolina Transitional Autonomous Vehicle Lane-Changing (NC-tALC) dataset and uses it to characterize mandatory lane-changing behavior of transitional automated vehicles (tAVs). It quantifies the evolution of lead–lag gaps throughout the lane-change process and examines how potential collision risk develops during the maneuver. A controlled field experiment comprising 78 mandatory lane-change trials was conducted on a public roadway in Apex, North Carolina. Four instrumented vehicles created repeatable traffic conditions while varying the lane changer's initial position within the candidate target gap. High-resolution RTK-GNSS/INS trajectories were processed to identify key timestamps, calculate lead, lag, and lane-change gaps, and estimate interactions using time-gap- and speed-based surrogate safety measures. Despite substantial differences in initial conditions, lead and lag gaps consistently converged toward a relatively narrow range near lane crossing. Potential collision risk increased as the maneuver progressed, peaked near physical lane entry, and was dominated by interactions with the target-lane leader. Lane-change completion did not necessarily coincide with the disappearance of collision risk. This study provides one of the first controlled empirical characterizations of the complete mandatory lane-change process of tAVs using repeatable public-road experiments. The NC-tALC dataset supports analysis of behavioral and safety evolution throughout the maneuver rather than only at the gap-acceptance instant. The dataset and findings provide empirical benchmarks for evaluating automated lane-changing behavior, calibrating behavioral models, and validating simulation and safety assessment methods for mandatory lane-change scenarios.

Continuous cuffless blood pressure (BP) monitoring remains challenging due to motion artifacts, physiological variability, and the limited robustness of conventional pulse transit time (PTT) models under dynamic conditions. Many prior approaches rely on multi-second windows to stabilize estimation, an assumption that is frequently violated during real-world monitoring with intermittent signal corruption. Here, we show that discriminative BP-related information is preserved at the single-beat level and present a lightweight multi-modal wearable framework for continuous BP estimation. The system integrates synchronized chest electrocardiography (ECG) and ear-clip reflectance photoplethysmography, each co-located with a 6-axis inertial measurement unit to provide motion context. We introduce a hybrid learning architecture in which a one-dimensional convolutional neural network extracts a 64-dimensional embedding from individual PPG beats and fuses it with 30 physiology-grounded features, including PTT statistics and heart rate variability, followed by LightGBM regression. The method was evaluated using a multi-phase stress protocol ($n=10$) and the PulseDB public dataset with subject-disjoint validation. Across 30 independent runs, the model achieved mean absolute errors of $4.02 \pm 0.21$~mmHg for systolic BP and $1.79 \pm 0.05$~mmHg for diastolic BP, corresponding to a 28.2% reduction in combined MAE relative to baseline models. By enabling beat-wise estimation without long temporal context, this framework supports computationally efficient cuffless BP monitoring suitable for wearable deployment under practical resource constraints. The source code for this work is available at https://github.com/SYMBIOX-Lab/BP-wireless.

Energy storage is increasingly relied upon to meet short-term demand uncertainties from renewable variability and electrification. Unlike conventional generators, storage's contribution to reliability is policy-dependent and balances near-term arbitrage against future scarcity risk. We study how demand uncertainty alters such dynamic storage operation and how these operating decisions propagate into long-run investment outcomes. We formulate storage operation as an average-cost Markov decision process and embed the resulting stationary policies into a stylized capacity expansion framework. Demand uncertainty induces a precautionary storage policy which hedges against stochastic scarcity, leading to materially different post-storage demand distributions relative to perfect-foresight benchmarks. We additionally demonstrate that the reliability externality characteristic of electricity markets interacts with uncertainty in a manner that uniquely distorts both storage operation and investment.

Existing single-domain and multi-task audio systems remain limited in directly organizing heterogeneous audio components, ambience, and multiple roles into long-form temporal scenes. We present Qwen-Audio-3.0-Gen-Preview, a unified non-autoregressive framework that uses a Diffusion Transformer (DiT) and a shared variational autoencoder (VAE) to generate the complete mixed waveform. Prompt enhancement converts free-form requests into structured temporal records that are rendered as textual conditions, while a two-stage data curriculum and semantic conditional views train the proposed model to use these conditions across standalone and mixed-scene audio. A shared continuous VAE compresses 48kHz stereo waveforms into 25Hz latent sequences and incorporates semantic supervision, providing one representation for heterogeneous audio. On the public reference-conditioned benchmark, speaker similarity is the proposed model's clearest strength across all three subsets. Across the multi-speaker and rich-timeline benchmarks, its clearest comparative strengths are cross-turn consistency in both languages and temporal localization, respectively. On AudioCaps, its advantages are concentrated in evaluations using large audio-language models and AudioBox. These results demonstrate the potential of unified generation for temporally structured audio without task-specific branches.

In this paper, we propose Probabilistic Denoising ISAC (PDISAC), a framework built on a multi-bit slot-partitioned ISAC waveform: by partitioning each maximal-length sequence into alternating pilot and data slots, we embed multiple bits per sequence through symbol-level spreading, multiplying the data rate while every chip retains the deterministic radar code. The added throughput, however, injects data-dependent, non-white sidelobes into the range-Doppler (RD) heatmap that degrade matched-filter (MF) sensing. Rather than modifying the MF receiver, we develop RDPDNet, a lightweight probabilistic denoising network inserted between RD-map formation and constant-false-alarm-rate detection; training it with an adversarial frequency-mixup mechanism, we suppress the data-induced sidelobes and thermal noise without knowledge of the embedded symbols. We further characterize the statistics of the geometry-determined channel. The fundamental performance limits of the design are then analyzed through an analytical lower bound, a semi-analytical bit error rate (BER), and an average capacity that tie the slot allocation and sequence length to the sensing-communication trade-off. Through analytical and numerical results over a realistic urban geometry, we show that RDPDNet absorbs most of the data-embedding sensing penalty and markedly lowers the RMSE at low SNR, while the conventional data-free chain attains the bias-adjusted benchmark at high SNR. Moreover, increasing the slot allocation raises the data rate at the expense of a higher BER, exposing a tunable sensing–communication trade-off.

Sensing ego-velocity estimation is fundamental to state estimation in visually degraded environments, where camera- and LiDAR-based pipelines can become unreliable. Millimetre-wave radar is well suited to these conditions because it provides direct Doppler velocity sensing and remains robust to poor illumination, textureless scenes, and airborne particulates. However, conventional radar ego-velocity pipelines typically apply constant false alarm rate (CFAR) thresholding to convert dense radar spectra into sparse point clouds, prematurely discarding sub-threshold returns that may still retain useful Doppler motion cues. We present Dense Soft Weighting, an analytic radar front-end that maps every range-Doppler cell to a continuous confidence metric rather than enforcing a binary detection threshold. Ego-velocity is then estimated using a deterministic robust weighted least-squares formulation, while the same weighted measurements provide a closed-form, measurement-derived velocity covariance for integration with a shared inertial back-end. The method requires no platform-specific training data or learning-based uncertainty model, supporting transfer across single-chip radar configurations. Across two public datasets and one self-collected dataset, Dense Soft Weighting reduces mean absolute pose error by 31-45% relative to the strongest CFAR point-cloud baseline under an identical inertial back-end, while running in real time on embedded hardware.

Vertical farming enables high productivity and stable crop production under controlled conditions, but its economic feasibility remains limited by electricity demand for artificial lighting and climate control. This study develops a surrogate-based optimization framework for cost-minimizing lighting management in hydroponic vertical farms. A key contribution is a procedure for converting crop-energy response data into relationships suitable for mathematical programming. The method can be applied to experimental datasets or outputs from validated dynamic models, provided that relevant ranges of control variables, crop stages, and energy responses are represented. The framework is applied to lettuce cultivation in an industrial-scale vertical farm in northern Italy. Synthetic data generated by a verified agri-energy model are used to derive surrogate relationships for fresh biomass growth, leaf area index, and electricity demand for lighting, heating, and cooling. These relationships depend on photosynthetic photon flux density, crop stage, and outdoor temperature. Different temporal aggregation levels are examined to evaluate the trade-off among surrogate accuracy, scheduling flexibility, and computational compactness. The surrogate model reproduced crop and energy trends of the reference model with sufficient accuracy for optimization. Compared with fixed-lighting benchmarks, optimized schedules reduced electric energy consumption by up to 15.9% and electricity cost by up to 17.8%, while achieving the target harvest weight. Results indicate that moderate light intensities combined with flexible photoperiods are more cost-effective than high-intensity lighting under the investigated conditions. The proposed framework offers a tractable and generalizable approach for integrating crop growth, energy demand, and electricity price variability into vertical farming lighting strategies.

Accurate channel state information (CSI) is critical for downlink (DL)-multi-user (MU)-multiple-input multiple-output (MIMO) systems, where feedback delays and mobility can degrade precoding performance. To ensure reliable beamforming and interference mitigation, CSI prediction is required. In practical systems, full CSI feedback is often infeasible due to signaling overhead, so transmitters rely on partial CSI reported by the receivers. In this work, we propose a Gaussian mixture model (GMM)-based prediction framework for MIMO-orthogonal frequency-division multiplexing (OFDM) channels under partial feedback using Gram-square-root factorization. To address the high dimensionality, we introduce an efficient parameter reduction technique that exploits structured covariance matrices, significantly lowering complexity without noticeable performance degradation. This reduction is based on the Gram-square-root factorization and remains of interest even when full CSI is available. Simulation results demonstrate that GMMs achieve the highest prediction accuracy and correctly capture the underlying channel subspaces, which is essential for effective MU-precoding. The proposed method outperforms classical baselines such as zero-order hold (ZOH), first-order hold (FOH), and linear minimum mean squared error (LMMSE) predictors, and an advanced neural network (NN)-based predictor. Notably, the parameter-reduced partial CSI GMM achieves performance comparable to that of full CSI prediction, highlighting its ability to efficiently model the channel structure under limited feedback.

An important problem in neuro-engineering is the stabilization of neural fields. In applications, it is often assumed that the actuator placement can be chosen arbitrarily. In this work, we investigate the stabilizability of controlled Amari-type neural fields where the control input is prescribed to act only on a fixed subset of the neural field. We show that the linearized neural field is open-loop stabilizable under suitable assumptions on the interaction strength and a mild relative density assumption on the control set. Our geometric assumption requires that the volume of each cube intersected with the control set must be bounded below. As a consequence, we derive closed-loop stabilizability of the neural fields, under sensor/actuator placement constraints. Numerical simulations are used to illustrate the results and obtain empirical estimates on the control cost.

Many scientific fields rely on standard benchmarks and shared platforms to improve review and reproducibility, but autonomous systems research still lacks widely accepted open hardware. Where standardization has emerged, progress has accelerated. This is especially evident in autonomous racing, where teams often build custom systems or buy niche, expensive vehicles, making control and robotics research and education hard to compare and reproduce. High costs also limit access outside well-funded labs, while affordable educational robots are often underpowered. To address this gap, we present NeoRacer, an open-source 1:12 scale autonomous racing platform. It is built around an NVIDIA Jetson Orin Nano (67 TOPS), a 270{\deg} LiDAR, a 120 fps global-shutter camera, and a 9-axis IMU. NeoRacer ships pre-assembled for USD 2,699, offering over 3x the compute of comparable platforms at less than half the cost of the nearest pre-assembled alternative. Co-developed by the Neobotics Foundation and Seeed Studio, and manufactured by Seeed Studio, NeoRacer combines open hardware and software design with scalable, repeatable production. The modular, extensible platform provides a standardized benchmarking environment for autonomous racing algorithms across institutions. We describe the hardware/software architecture, design decisions from two pilot deployments (MIT IAP, 15 students; BU CPS Lab, 10 students), and key cost-performance tradeoffs. Hardware is licensed under CERN-OHL-S v2 and software under GPLv3, with all design files, firmware, and ROS2 packages publicly accessible.

Wireless positioning is evolving from legacy cellular and standalone satellite navigation toward hybrid, high-accuracy, three-dimensional (3D), and network-verifiable frameworks for 5G Advanced, 6G, and non terrestrial network (NTN) systems. This shift is driven by intelligent transportation, unmanned aerial vehicle (UAV) operation, low-altitude economy services, public warning, and regulated NTN use cases that require not only accurate location estimates, but also vertical awareness and verification confidence. This survey reviews the evolution from Long Term Evolution (LTE) and Global Navigation Satellite System (GNSS) positioning to New Radio (NR), Release-18/19 positioning enhancements, and NTN-enabled 3D positioning. It synthesizes observable families, 3rd Generation Partnership Project (3GPP) standard evolution, method-level tradeoffs, and open challenges for hybrid terrestrial network (TN) NTN designs, with emphasis on standardization impact, vertical observability, reliability-aware measurement selection, and network-side verification.

Memristors are promising devices for applications such as non-volatile memory, neuromorphic computing, logic circuits, and analog signal processing. The development of such systems requires accurate simulations based on models that reproduce the electrical behavior of real devices under both continuous and pulsed excitation. This work presents the development of a simulation environment for a volatile TiO2-based memristor. Experimental measurement data are analyzed to verify the memristive behavior of the device and to identify a suitable model. The model parameters are then optimized to match the measured characteristics. The resulting model is implemented in SPICE and validated by comparing simulation results with measurement data. The comparison shows a good agreement between simulation and experiment, demonstrating that the developed model is suitable for reproducing the electrical behavior of the investigated memristor and can be applied in circuit-level simulations, as demonstrated by a leaky integrate-and-fire neuron.

Blood glucose estimation is the cornerstone of model-based decision support (DS) and Automated Insulin Delivery (AID) systems. Control systems that rely on physiologic/compartmental models depend heavily on model parameterization, which is either defined using population values or personalized through the user's data. Often, the model parameters are defined as constants. However, under real-world free-living conditions, fixed parameters can limit the accurate reconstruction and estimation of glucose levels and states. In this paper, we propose and discuss a recursive filtering framework for online joint state estimation and parameter identification in nonlinear, time-varying physiological models for Type 1 Diabetes (T1D). Specifically, we employ a Rao-Blackwellized Stein Variational Gradient Descent (RBSVGD) filter to compute the joint posterior distributions of model states and parameters. The proposed approach is applied to the Hovorka glucose-insulin model and validated using data generated by the the Oregon Health & Science University (OHSU) simulator across 20 virtual patients. We perform a comparative analysis against: (i) a standard Extended Kalman Filter (EKF) with fixed model parameters, and (ii) an Augmented Extended Kalman Filter (AEKF) for joint state-parameter estimation. The results demonstrate that the proposed RBSVGD-based framework outperforms both EKF and AEKF approaches not only in terms of the accuracy of glucose estimation, but also in terms of estimated model parameters.

State-of-the-art intracortical brain-to-text systems pair a neural-sequence phone decoder with an external language model. Two design axes remain underexplored: whether selective state-space models (Mamba) improve on recurrent decoders, and how the output target (phonetic vs.\ character) interacts with that choice. On the public Brain-to-Text '25 benchmark, we study a controlled 2x2 grid (GRU vs.\ hybrid Mamba decoder; phonetic vs.\ character targets) trained with a CTC objective under one reproducible protocol. The recurrent baseline remains strongest: the best phonetic GRU reaches 12.62% PER and 21.19% WER, while the best textual GRU after LM rescoring reaches 13.39% CER and 26.28% WER. The Mamba hybrid is competitive but does not surpass it. Ablations isolate architectural contributions, and error analysis shows representation-dependent failures: articulatory-like phoneme confusions vs.\ lexical and word-boundary errors.

Accurate identification of Alzheimers disease (AD) using resting-state functional magnetic resonance imaging (rs-fMRI) remains challenging due to the high dimensionality, noise, and complex inter-regional dependencies inherent in functional brain connectivity, which limit the effectiveness of traditional approaches based on handcrafted connectivity features or conventional machine learning models. In this work, we present an attention-based deep learning framework for Alzheimers disease classification that operates directly on rs-fMRI functional connectivity matrices by treating brain regions as tokens and employing a Transformer-inspired self-attention mechanism to model long-range and global functional dependencies across distributed brain networks. The proposed framework learns discriminative functional representations without reliance on manual feature engineering and is evaluated on a longitudinal cohort from the Alzheimers Disease Neuroimaging Initiative (ADNI) comprising cognitively normal and Alzheimers disease subjects with multiple visits. A subject-wise evaluation protocol is adopted to prevent information leakage across visits, and class-weighted optimization is incorporated to address mild class imbalance. Experimental results for binary AD versus cognitively normal classification demonstrate that the proposed attention- based rs-fMRI model achieves an accuracy of 88.95% and a ROC-AUC of 0.90, along with a favorable precision-recall balance, highlighting the effectiveness of self-attention-driven functional connectivity modeling as a robust and interpretable approach for Alzheimers disease detection using resting-state fMRI.

Zero-shot text-to-speech (TTS) clones a voice from a short audio prompt, but this reliance on reference audio is a barrier when only visual information is available, e.g. for historical figures or video-game characters. In this work, we propose a Face-to-Speech (F2S) framework that predicts a plausible voice from a static facial image. A lightweight Face Adapter, together with soft-tuning of the face encoder's upper blocks, aligns face-recognition features with the style space of a frozen StyleTTS 2 model, kept frozen during training. We evaluate on held-out identities from LRS3, a large-scale audiovisual corpus of English TED-talk videos. The synthesized speech is highly natural (UTMOS 3.7-4.0, matching or exceeding the 3.61 of ground truth), face-to-voice retrieval is consistently above chance, and the generated voice is consistent with the target speaker. Without any retraining, an English-trained adapter also produces fluent Spanish speech, indicating that the face-to-style mapping is largely language-agnostic.

This paper presents the analysis, design, fabrication, and experimental validation of a dual-mode frequency/amplitude modulator based on a time-modulated varactor diode. By exploiting the varactor as a time-varying capacitor in combination with an operational amplifier configured as an inverting integrator and a passband filter, the proposed circuit generates frequency-modulated (FM) signals in an efficient manner. Amplitude-modulated (AM) signals can also be obtained with a simple modification. The implementation, realized in microstrip technology, leverages the unique properties of time-modulated electronic components, particularly their inherent frequency-mixing capability. Analytical expressions are derived to predict the characteristics of the generated waveforms, and their accuracy is verified through numerical simulations performed in Keysight ADS. A microstrip PCB prototype is then fabricated and experimentally characterized. The measured results show excellent agreement with both the theoretical predictions and the numerical simulations. The proposed approach demonstrates the potential of time-varying capacitors as an attractive alternative to conventional FM techniques for telecommunications and radar applications.

This work presents a comprehensive analysis and design of global sensitivity-based input shapers for a 3D Unmanned Aerial Vehicle-payload system, emphasizing robustness against uncertainties in payload mass and rope length. The proposed approach also leverages the Shapley value concept in controller design to systematically account for uncertainties, thereby reducing the controller's sensitivity to unknown parameters. To validate the effectiveness of the methodology, numerical simulations are conducted, comparing the proposed controller against non-robust, robust, and minimax designs. The results demonstrate that the standard global sensitivity or Shapley-based input shapers improve performance and offer a promising framework for uncertainty-aware control in aerial payload transport.

Cover song generation (CSG) should preserve the melodic and linguistic content of a reference song while recreating the remaining musical components. The state-of-the-art model SongEcho utilizes $F_0$ sequences and voiced/unvoiced (V/UV) tags for conditioning; however, implicit linguistic information from V/UV tags cannot guarantee lyric accuracy, leading to a high phoneme error rate (PER). Inspired by singing voice synthesis (SVS), we propose MPEcho, which integrates a phoneme encoder and a length regulator (LR) into the SongEcho framework. By providing explicit phoneme-level conditioning and precise temporal boundaries, MPEcho significantly reduces PER. To enable this, we developed Phonsa, a Whisper-based automatic transcription model that provides high-precision phoneme-level annotations for singing voices, overcoming the scarcity of high-quality audio-phoneme pairs. Experimental results validate the effectiveness of Phonsa for alignment and MPEcho for end-to-end CSG. The audio samples, code and weights can be accessed from https://lonian6.github.io/MPEcho.github.io/.

Analyzing female pelvic MRIs is challenging, especially for evaluating endometriosis, where visual features are influenced by several factors, including anatomical complexity, technical variability, and inter-reader variability. Here, we evaluate a radiomics-based pipeline for patient-level endometriosis subtyping using the publicly available UT-EndoMRI dataset. We extract radiomics features from manually segmented uterine and ovarian regions and compare several multi-scale feature representations and feature-selection strategies. We train supervised classifiers to distinguish patients with at least one endometrioma from those without, and perform an unsupervised perturbation analysis to assess whether radiomics profiles reveal reproducible patient subgroups. The best supervised performance is achieved using raw Wavelet-derived features and a Gradient Boosting classifier, yielding an AUC of 0.80. However, this model produces several false positives, resulting in low specificity. ComBat harmonization does not consistently improve performance, suggesting that post hoc harmonization is insufficient in a small, multi-site cohort in which acquisition groups contained very few patients. Using an unsupervised clustering analysis, we identify reproducible but poorly separated partitions that remain associated with acquisition variables. Overall, these results suggest that pelvic MRI radiomics contain a preliminary signal for endometriosis subtyping, while highlighting the fragility of radiomics-based subtyping in small, multi-site datasets.

Centrally-managed Wi-Fi solutions are increasingly leveraging Distributed Artificial Intelligence (AI) to predict key operational statistics of Access Points (APs) and proactively optimize network performance. In this context, Clustered Federated Learning (CFL) represents a fitting methodology, enabling the generation of multiple AI models that account for diverse statistical properties of the APs data distribution. However, identifying informative clusters for grouping APs models remains a significant challenge. In this paper, we address this problem by proposing a novel CFL tool integrating a two step clustering procedure. Initially, multiple clustering solutions are generated and filtered based on a minimum set of desired clustering criteria. Subsequently, if no solutions meet sufficient quality metrics, a global model is produced by aggregating all AP models. Otherwise, the final clustering solution is selected as the one that maximizes the informativeness (quantified via differential entropy) for the smallest cluster. Our results, focusing on a Wi-Fi traffic prediction problem, demonstrate that the developed CFL tool achieves the best predictive performance among all evaluated distributed strategies and the lowest communication and energy footprint among the clustered ones, exceeding the cost of single-model FL only in the regimes where it markedly improves accuracy.

To serve the volumetric air-ground space, uncrewed aerial vehicles (UAVs) are urgently needed. Yet, relying on them for integrated sensing and communication (ISAC) introduces two key challenges: 1) dynamic and imbalanced ground communication demand, and 2) limited observation diversity for sensing. To address these issues, a cross-region cooperative framework is designed to coordinate UAV swarms. Specifically, a service-driven regional partitioning scheme is proposed to support traffic-aware UAV communication, and an adaptive handshaking mechanism is introduced to improve cooperative sensing accuracy by mitigating residual inter-region phase errors with controlled synchronization overhead. Based on these designs, a region-level multi-agent proximal policy optimization (MAPPO) framework with centralized training and decentralized execution (CTDE) is developed for cross-region cooperative decision-making. Simulation results demonstrate that the proposed method achieves a communication quality-of-service (QoS) of approximately 90% and reduces the Cramér-Rao bound (CRB) by about 45% compared to conventional baselines.