Audio and Speech Processing
PHAST-Net: Attention-Guided, Physics-Informed Network for Estimation of Ideal Time-Frequency Representations
James M. Cozens and Simon J. Godsill
We introduce PHAST-Net, an
attention-guided, physics-informed network for unified estimation of Ideal Time-Frequency Representations (ITFRs), spanning spectral, tempo-based, metrical, and harmonic representations such as Spectrograms, Tempograms, and Metrograms. PHAST-Net learns a mapping from a constellation of wavelet transforms, specifically the proposed Continuous Log-frequency Adaptive Wavelet Transform (CLAWT), to high-resolution, cross-term-suppressed time-frequency representations. The proposed constellation of CLAWTs is strategically selected through Wigner-Ville kernel analysis to provide orientation-diverse coverage in a log-frequency time-frequency plane tailored to harmonic signal structure. PHAST-Net further incorporates a proposed physics-informed auxiliary reprojection loss designed to match the CLAWT-domain reprojections of the predicted and target ITFRs using the corresponding CLAWT kernels during training. This auxiliary objective promotes transform and energy-distribution consistency, mitigates target sparsity, and regularises optimisation.
Attention layers further promote effective cross-term suppression across the input constellation. The log-frequency formulation also enables Harmonic PHAST-Net, which estimates a Harmonic ITFR that isolates fundamental structure, supporting robust fundamental-only representations for
speech and music, such as derived fundamental Tempograms and Metrograms. We further introduce Spline-PHAST-Net, which parameterises detected and associated time-frequency ridges as continuous spline trajectories, enabling arbitrary-grid re-rendering and signal reconstruction. Trained on a procedurally generated
dataset, PHAST-Net demonstrates improved accuracy over representative time-frequency analysis methods, providing a unified framework for high-resolution, cross-term-robust analysis of
speech, music, and broader nonstationary signals.
Read the full abstract ▾
Systems and Control · Cross-listed from cs.RO
Autonomous Subsea Cable Search and Tracking with Graph-Optimised Priors and Visual Tracking
Ibrahim Fadhil Djauhari, Adrian Bodenmann, Samuel Simmons et al. (+6 more)
Global communications rely on subsea cable infrastructure that remains vulnerable to damage from natural hazards and human activity. Autonomous
underwater vehicles (AUVs) offer an efficient means to inspect long sections of exposed cable, but uncertainty in cable route maps, small cable diameters and partial burial makes continuous tracking a challenge. This paper presents a novel cable search and tracking method that leverages uncertain prior cable route maps. Graph-based optimisation continuously update the cable route to remain consistent with visual observations. Route uncertainty is constrained as a function of distance from observations using physics-based catenary models that account for cable parameters (i.e., lay depth, diameter, and density), bounding the search space to physically feasible regions and improving search efficiency. Cable detection is performed using a semi-supervised classifier running in real-time on-board a camera-equipped AUV. These detections both update the graph-based optimisation and enable visual cable tracking. When tracking is lost due to misclassification, burial or imperfect control, the bounded search space enables efficient recovery. The approach was demonstrated in field trials using the University of Southampton's Smarty200 AUV. The system successfully located the cable despite deliberate errors in it initial cable route map, updating this to be consistent with observations and using visual tracking to inspect up to 59% of a 120m test cable, with successful recovered after tracking loss.
Read the full abstract ▾
All authors Ibrahim Fadhil Djauhari, Adrian Bodenmann, Samuel Simmons, Cailei Liang, David White, Susan Gourvenec, Tom Bennetts, Darryl Newborough, Blair Thornton
Systems and Control
Two-Stage Optimization for Dynamic Line Rating and Energy Storage Deployment
Abanish Tiwari, Phurba T. Sherpa, Chandan Chaudhary et al. (+2 more)
The increasing penetration of distributed energy resources (DER) and weather-driven variability has intensified congestion and reliability stress in transmission networks. Strategies that enhance the utilization of existing infrastructure, such as static line ratings (SLR) and energy storage systems (ESS), have therefore become necessary. SLRs rely on conservative ambient assumptions and often understate thermal limits, whereas dynamic line ratings (DLR) adjust capacity according to weather conditions and unlock additional transfer capability. Energy storage systems provide temporal flexibility, but their transmission-level effectiveness depends on proper siting and sizing. This paper proposes a two-stage optimization method for joint placement of DLR installations and utility-scale energy storage. In the first stage, a mixed-integer linear program selects DLR corridors and ESS buses by minimizing operating cost, DER curtailment, and load-shedding penalties subject to DC power flow and investment constraints. In the second stage, the model determines ESS energy capacity and operating schedules under ambient-driven line ratings. Ambient weather data is used to generate DLR profiles, and sequential Monte Carlo simulation is applied to assess system adequacy. The proposed method, when deployed on the modified IEEE RTS 24-bus system, shows that coordinated DLR and ESS planning improves transmission capability, mitigates congestion, and strengthens system adequacy under weather variability.
Read the full abstract ▾
All authors Abanish Tiwari, Phurba T. Sherpa, Chandan Chaudhary, Mohammed Ben-Idris, Joydeep Mitra
Systems and Control · Cross-listed from cs.MA
Decentralized Autonomous Traffic Management through Corridor Networks
Jasmine Jerry Aloor, Aadarsh Govada and Hamsa Balakrishnan
As autonomous aircraft are introduced at scale and traffic density increases, centralized management becomes insufficient to coordinate the large numbers of crewed and uncrewed aircraft. Dedicated Advanced Air Mobility (AAM) corridors have therefore been proposed for organizing high-density autonomous traffic flows. The desire to scalably provide autonomous aircraft flexibility in trajectory planning motivates the development of decentralized approaches to traffic management in AAM corridors. In this work, we extend a multi-
agent reinforcement learning (MARL) approach to address the challenge of decentralized traffic flow management in air corridor networks. We test policies trained in a single-corridor setting on increasingly complex multi-corridor networks with combinations of merges and splits in a zero-shot manner. Experimental results demonstrate that learned behaviors transfer well to scenarios with varying traffic density, network geometry, and heterogeneous vehicle performance, without needing centralized coordination or model retraining. We evaluate system-level performance in terms of conformance to corridor boundaries, completion rates, average speeds, distance traveled, and maintenance of inter-aircraft separation. We find that although our policies require only locally coordinated entry, traversal, and exit behaviors, they collectively produce desirable traffic flows through the corridor network.
Read the full abstract ▾
Signal Processing
High Speed High Signal-to-Noise Ratio Antenna Measurements – Demonstration for UAV-Based Near-Field Measurements of Modulated Terrestrial Navigation Signals
Thomas F. Eibert, Denis Unruh, Thomas Mittereder et al. (+1 more)
Antenna measurements with high signal-to-noise ratio (SNR) require long measurement or integration times of the receiver and can, thus, lead to a very long duration of the measurements, especially if many frequency and spatial samples need to be collected. In order to speed up such measurements, an approach is presented, which collects all measurement samples with short measurement times, performs a
Fourier transform of the measurement samples, bandpass filters the desired measurement signals with a small bandwidth, and obtains high-SNR measurement samples according to the short measurement times by inverse
Fourier transform. This approach can be utilized with single-frequency continuous wave (CW) transmit signals, but also with transmit signals containing several discrete frequency components, as, e.g., found for periodically modulated CW carriers. The approach is first worked out and demonstrated for simulated test data. Next, it is utilized for the processing of modulated near-field (NF) measurement data collected via an uninhabited aerial vehicle (
UAV) at a Doppler high-frequency omnidirectional
radio range (DVOR) and at the localizer of an instrument landing system (ILS). The extracted CW NF data is transformed into the far field (FF) and diagnostic information is obtained from the underlying inverse source solutions.
Read the full abstract ▾
All authors Thomas F. Eibert, Denis Unruh, Thomas Mittereder, Alexander H. Paulus
Systems and Control · Cross-listed from cs.LO
Digital Twins Need Feedback
Guo-Qiang Zhang
Digital twins are too often described as realistic simulations, anatomical avatars, dashboards, or data mirrors. Those artifacts can be useful, but they miss the defining property of a digital twin: bidirectional feedback between a physical counterpart and a virtual counterpart. The physical system continuously updates the virtual one; the virtual system informs actions that change measurement, intervention, operation, or governance in the physical world. We propose such a bidirectional feedback as the organizing principle for digital twins and apply it to a nested, multi-scale hierarchy of biological and social organization, in which lower-level units combine into higher-level systems, producing desirable properties at each level, from
cells and tissues to organs, individuals, organizations, and population at large. Neuroinformatics is a stress test for this view because
brain health, dementia, epilepsy, and other neurological diseases require the integration of
cells,
circuits, behavior, care pathways, and the translation of discovery to practice. Examples from epilepsy care and consortium-scale
brain-
cell atlas production show that digital twinning is not merely multi-scale modeling. It is a rich, multidisciplinary paradigm of computing for designing, governing, and driving feedback loops that turn data into accountable action.
Read the full abstract ▾
Signal Processing
Sensor-Stack Limits on Contactless In-Bed Body Position: A 20-Subject Multimodal Radar + Thermal LOSO Characterization
Dovy Paukstys
Contactless in-bed body-position inference can be limited by the sensor representation the host receives rather than by the classifier. We characterize a bedside 60 GHz frequency-modulated continuous-wave (FMCW) radar that reports only on-device constant-false-alarm-rate (CFAR) point clouds, together with a low-resolution thermal array (24x32 nominal, 24x16 effective), on 20 subjects under leave-one-subject-out (LOSO) evaluation. Two tasks share the cohort: 273 operator-directed in-bed posture holds (148.7 minutes) and a per-second bed-presence timeline (8,817 scored seconds). The cohort is a friends-and-family convenience sample (13 minors, ages 5 to 68, six families), and every session used the same bed in one room with the subject uncovered, so the figures describe this setup rather than a population. Bed presence reaches a 0.871 per-subject median balanced accuracy (95% CI 0.796 to 0.910). For four-class posture, nested LOSO, in which every selection and fitting step sees training subjects only, gives 0.646 balanced accuracy (per-subject median 0.683). Prone recall is 0.45 at a precision of 0.42, so prone is not usefully detected. Version 1 reported 0.674 for a stacked ensemble picked on the folds it was scored on; this version replaces that figure with a nested estimate and corrects the bed-presence accounting and the description of the recording setting. Thermal resolves left versus right (lateral swaps of 35 to 42% with radar alone, 8% with thermal alone). The supine-versus-prone breathing cue shows up in the CFAR output only as a group shift (Cohen's d = 0.61), with a clean per-hold peak in 8.4% of holds. The next hardware test is raw range-FFT access, not further classifier tuning on CFAR detections.
Read the full abstract ▾
Systems and Control
Industrial electrification in the era of data centers: A Bayesian Optimization approach for grid-aware large load allocation
Jiyong Lee, Erhan Kutanoglu, Michael Baldea et al. (+1 more)
Large loads from industrial electrification and data centers are reshaping the planning and operation of the power grid. Identifying optimal large load siting decisions while accounting for transmission congestion is key to reducing expansion cost and operational risks. In this paper, we propose a leader-follower bilevel optimization framework to identify optimal large load allocation strategies. The leader determines the allocation of large loads, while the followers determine grid expansion cost and transmission utilization. This modeling approach explicitly integrates strategic planning with detailed short-term operational decisions. Moreover, we develop a
Bayesian Optimization approach to efficiently solve the bilevel optimization problem by treating the followers as a black box. We use the framework to study large-scale load allocation from electrified oil refineries and data centers on a synthetic power grid that resembles key characteristics of the Texas (ERCOT) system. The results show that these large loads compete for electricity, and under high-load scenarios, data center demand is distributed across the entire grid, avoiding regions with high demand from industrial electrification.
Read the full abstract ▾
All authors Jiyong Lee, Erhan Kutanoglu, Michael Baldea, Ilias Mitrai
Signal Processing
Symbol Rate-Code Rate Trade-offs for IM/DD 200G/400G per Lane LPO Transceivers
José Núñez-Kasaneva, Yunus Can Gültekin, Stefanos Dris et al. (+3 more)
We analyze the symbol rate-code rate trade-off in bandwidth-limited IM/DD systems targeting LPO transceivers, using PAM-4/6/8 as candidate modulation formats. We use the capacity of the binary symmetric channel as an achievable information rate under hard-decision decoding, serving as a performance metric for 200G and 400G per-lane throughput targets. Our results show that reducing the FEC code rate below the KP4 baseline allows higher-order PAM formats to operate at substantially lower symbol rates than PAM-4 while meeting the throughput requirement.
Read the full abstract ▾
All authors José Núñez-Kasaneva, Yunus Can Gültekin, Stefanos Dris, Paraskevas Bakopoulos, Nikos Argyris, Gabriele Liga
Systems and Control · Cross-listed from cs.RO
A Relaxed Quadratic-Program-based Framework for Trajectory Tracking of Unicycle Robots with Singularity Avoidance
Hamza Tariq, Usman Ali and Adeel Akhtar
Dynamic feedback linearization (DFL) is a classical technique for trajectory tracking of unicycle-type mobile
robots, but the resulting DFL-based controller becomes singular when the linear velocity vanishes, rendering standard DFL-based controllers unsuitable for stop-and-reverse maneuvers. This paper proposes a quadratic-program (QP)-based optimal control framework that avoids this singularity, while establishing local Lipschitz continuity of the resulting feedback law. Our approach reformulates the DFL constraints as an equality-constrained QP with a slack variable, ensuring feasibility for all states and reference signals, including at points where the
robot's velocity vanishes. By introducing slack variables and tunable parameters, we demonstrate that the singular configuration can be avoided for a large class of reference trajectories. The effectiveness of the proposed approach for trajectory tracking is demonstrated through ROS 2-Gazebo simulations on a TurtleBot3 Waffle
robot. The code is available at https://gradslab.github.io/DFL_QP_Unicycle/
Read the full abstract ▾
Audio and Speech Processing
Don't Listen to Me: A Lightweight, Low-Latency Model for Own-Voice Cancellation in Far-Field Speech Enhancement
Mads Østergaard, Alexander Neergaard Zahid, Karl Ulbæk et al. (+3 more)
We introduce own-voice cancellation (OVC): removing a target (enrolled) speaker from a noisy multi-speaker mixture while preserving any remaining
speech. Framed as the complement of target speaker extraction, OVC addresses latency-induced own-voice artifacts that arise when a far-field device streams enhanced audio back to the user, as the round-trip time easily exceeds the perceptual threshold for own-voice distortion. We condition a time-domain model with only 2 ms algorithmic latency on a short enrollment utterance and
benchmark TD-SpeakerBeam alongside a lighter Mamba-MinGRU masker built from Mamba blocks with MinGRU temporal mixing. Replacing the ConvTasNet-based auxiliary network with a linear RNN encoder improves both signal-to-distortion ratio and predicted MOS while reducing compute. Results establish OVC as a practical, low-latency enhancement objective for far-field denoising.
Read the full abstract ▾
All authors Mads Østergaard, Alexander Neergaard Zahid, Karl Ulbæk, Andreas Hansen Bagge, Kenny Falkær Olsen, Rasmus Malik Høegh Lindrup
Signal Processing
Learning to Compute on Dirty Paper
Shreesal Shrestha, Kuranage Roche Rayan Ranasinghe, Giuseppe Thadeu Freitas de Abreu et al. (+1 more)
We propose a fully learning-based approach to integrated communication and computing (ICC) that combines dirty paper coding (DPC) with over-the-air computation. Each user employs a neural encoder with sinusoidal activations that learns to pre-cancel its own computing symbol as non-causally known interference, recovering modulo-like periodic structures consistent with
lattice-based DPC schemes. A joint neural decoder recovers all users' messages from the received signal, while a separate neural AirComp
estimator exploits a multi-slot block structure to estimate a target function of the computing symbols after the encoder-decoder network converges. To our knowledge, this is the first fully learning-based approach to jointly address DPC-based interference pre-cancellation and over-the-air computation in a unified framework.
Read the full abstract ▾
All authors Shreesal Shrestha, Kuranage Roche Rayan Ranasinghe, Giuseppe Thadeu Freitas de Abreu, Elza Erkip
Systems and Control · Cross-listed from cs.CR
A Hybrid Intrusion Detection System for Electric Vehicle Charging Infrastructure
Charukeshi Joglekar, Chijioke Eze, Danni Xiang et al. (+1 more)
The integration of Electric Vehicle Charging Stations (EVCSs) into the smart grid necessitates sophisticated digital infrastructure for their management and coordination, which expands the attack surface and makes both the power grid and EVCSs vulnerable to cyberattacks. This research addresses critical gaps in existing EVCS Intrusion Detection Systems (IDS) by proposing a hybrid IDS that integrates attack detection on both the cyber and physical layer of the EVCS ecosystem. The proposed hybrid IDS utilizes a dual-layer integration method, which combines network-based IDS (NIDS) and host-based IDS (HIDS). This approach facilitates for comprehensive monitoring of both network traffic through the NIDS and host-level activities via the HIDS, effectively addressing the unique challenges posed by the interconnected nature of EVCS ecosystems. Utilizing the recent CICEVSE2024
dataset, the IDS presented in this work performs multiclass classification across various attack types, including False Data Injection Attacks (FDIAs), reconnaissance, denial of service,
backdoor, and cryptojacking attacks. Experimental results demonstrate that our approach achieves excellent detection accuracy, with the NIDS component reaching 99.99% accuracy for network-based attacks and the HIDS component achieving 83.47% accuracy on FDIA, cryptojacking,
backdoor, all DoS, all Recon except Slowloris Scan attacks. This dual-layer detection significantly outperforms single-source detection approaches previously presented in literature.
Read the full abstract ▾
All authors Charukeshi Joglekar, Chijioke Eze, Danni Xiang, Antonello Monti
Audio and Speech Processing
Word Lengthening as a Function of Utterance Position: A Multi-Corpus Study
Mateo Cámara, José Luis Blanco, Juan Ignacio Godino-Llorente et al. (+2 more)
Efficient turn-taking requires interlocutors to predict turn endings within a few hundred milliseconds. Beyond syntactic and pragmatic completion, prosody (especially pre-boundary lengthening) supports projection. We test whether turn-final words are longer than mid-sentence words, whether this reflects prosodic modification rather than lexical choice, and where within the word it concentrates. We analyze four corpora spanning styles and two
languages (English, Spanish): Switchboard, Columbia Games, BU
Radio, and Glissando, with >500 speakers, $39{,}470$ turn-final and $206{,}268$ mid-sentence
tokens across $\sim39{,}500$ turns. Turn-final words are longer (mean ${\approx}191$\,ms; $d=1.14$). The effect persists in matched-word, within-speaker comparisons ($80$\,ms; $p<0.001$) and is localized mainly to the final syllable ($d=0.89$). Turn-final lengthening thus emerges as a robust, localized cue to floor transfer.
Read the full abstract ▾
All authors Mateo Cámara, José Luis Blanco, Juan Ignacio Godino-Llorente, Jeung-Yoon Choi, Stefanie Shattuck-Hufnagel
Systems and Control · Cross-listed from math.OC
Value iteration with stopping criterion: finite iterations, stability, and near-optimality guarantees
Mathieu Granzotto, Romain Postoyan, Dragan Nešić et al. (+2 more)
Value iteration (VI) is a cornerstone of dynamic programming that allows computing near-optimal feedback laws for general plant dynamics and cost functions. In practice, however, it must be stopped after finitely many iterations. This raises the question of when to stop the
algorithm so that the resulting policies and value functions achieve desirable properties, like given near-optimality bounds and stability. In this context, we study deterministic, discrete-time systems with infinite-horizon (possibly discounted) costs whose inputs are generated by VI. We equip VI with a generalized stopping criterion that encompasses existing choices while allowing new ones. Our aim is to analyze the properties of the policies and value functions at the final iteration. Under mild assumptions, we first show that VI indeed terminates in a finite number of iterations. We then establish that the final policies are stabilizing by properly designing the stopping criterion, and derive explicit near-optimality bounds characterized by this choice. These results offer a design framework for the stopping criteria that balances computational effort with stability and performance guarantees.
Read the full abstract ▾
All authors Mathieu Granzotto, Romain Postoyan, Dragan Nešić, Lucian Buşoniu, Jamal Daafouz
Audio and Speech Processing
Acoustic Landmark Detector based on Conformer and HuBERT
Mateo Cámara, José Luis Blanco, Juan Ignacio Godino-Llorente et al. (+2 more)
Acoustic landmarks (abrupt acoustic changes tied to
speech events) offer a linguistically grounded representation for
speech analysis. We study automatic landmark detection with Conformer models, evaluating 14 configurations spanning architecture, loss, label representation, feature extractor, and data conditions on 1 839 manually annotated utterances with eight landmark types. We propose Gaussian soft labels with per-class temporal spread (sigma=10-20 ms), improving F1-at-20 ms by 7.0% absolute vs. hard labels by modeling annotation variability. Frozen HuBERT features perform best without fine-tuning (F1-at-20 ms=0.77). Stops and fricatives are reliable (F1>0.80), while vowels remain challenging (F1 approx 0.55). On our corpus, our system reaches a 13.8% Landmark Error Rate (LER). This is not directly comparable to AutoLandmark (31.3%) or SpeechMark (56.5%), evaluated on a different corpus and metric. Per-class trends show detectability increases with event abruptness, consistent with Stevens' theory.
Read the full abstract ▾
All authors Mateo Cámara, José Luis Blanco, Juan Ignacio Godino-Llorente, Jeung-Yoon Choi, Stefanie Shattuck-Hufnagel
Audio and Speech Processing
An Acoustic Landmark Database of the English Lexicon via Articulatory Synthesis
Mateo Cámara, José Luis Blanco, Juan Ignacio Godino-Llorente et al. (+2 more)
Acoustic landmark theory treats
speech as organized around the acoustic consequences of articulatory gestures that shape the vocal tract and airflow. Progress is limited by the scarcity of large, unambiguously annotated landmark
datasets. We invert the problem by generating
speech from landmark patterns. Using the Pink Trombone physical vocal-tract synthesizer, we produce an English lexicon for two adult configurations (male, female). With direct control of gestures, we place landmark labels algorithmically at the exact times of their physical events (e.g., oral closures/releases). The corpus contains $>$200,000 synthesized words, rendered for both configurations with time-aligned annotations; intelligibility is measured with STOI. We leverage it for statistics across the lexicon from an articulatory-event view, reporting landmark frequencies and dominant cue patterns, and enabling quantitative studies plus training/benchmarking of automatic landmark detectors.
Read the full abstract ▾
All authors Mateo Cámara, José Luis Blanco, Juan Ignacio Godino-Llorente, Jeung-Yoon Choi, Stefanie Shattuck-Hufnagel
Systems and Control · Cross-listed from math.OC
Path-following Control of a Quadrotor using Quasi-Static Transverse Feedback Linearization
Mohamed Al Lawati and Adeel Akhtar
We propose a quasi-static transverse feedback linearization (QSTFL) controller for a quadrotor to follow a prescribed
geometric path, rather than a time-parameterized trajectory. In contrast to existing dynamic-feedback approaches, the controller does not introduce additional controller states. The thrust input is computed algebraically from the current state, eliminating the need for thrust-derivative measurements and numerical integration. The proposed design renders the path-following
manifold invariant, ensuring that trajectories initialized on the path remain on it for all future time, while simultaneously regulating tangential velocity and yaw. We establish a diffeomorphic coordinate transformation and prove local exponential stability of the path-following
manifold. In addition, closed-form expressions are derived for the thrust and torque inputs. Compared with dynamic-feedback constructions, the controller requires inversion of only a $3\times 3$ decoupling
matrix rather than a $4\times 4$ one, leading to a simpler control law and reduced computational complexity. Numerical simulations demonstrate the effectiveness of the proposed method. Code and animations are publicly available at \footnotesize{\texttt{\href{https://gitlab.com/a5akhtar/quasistatic-tfl-
uav/}{https://gitlab.com/a5akhtar/quasistatic-tfl-
uav/}}}.
Read the full abstract ▾
Signal Processing · Cross-listed from cs.LG
Efficient Network Inference via Hardware-Aware Architecture Search, Model Pruning & Quantization
Lucas Heublein, Mark Deutel, Axel Plinge et al. (+1 more)
Embedded global
navigation satellite system (GNSS) interference monitoring requires fast and
memory-efficient inference to process large volumes of raw in-phase and quadrature (IQ) samples in real time. At the same time, increasingly expressive deep neural networks (DNNs) are needed for robust interference classification and characterization across diverse signal conditions. This creates a fundamental tension between predictive performance and deployability on resource-constrained hardware. In this paper, we investigate efficient network inference for GNSS interference characterization using iterative structured
pruning, post-training static quantization, and hardware-aware zero-shot neural architecture search (NAS). Starting from MCUNet as a compact baseline, we analyze how model compression and automated architecture optimization affect model size, computational complexity, and
memory usage while maintaining task performance. Experiments on a GNSS interference
dataset, covering both classification and generalized characterization, show the benefits of combining compression and hardware-aware design for embedded deployment. Our results provide practical guidance for developing compact machine learning (ML) models for real-time GNSS interference monitoring on embedded platforms (iMXRT1062 MCU, Raspberry Pi Zero 2W, and Raspberry Pi 5).
Read the full abstract ▾
All authors Lucas Heublein, Mark Deutel, Axel Plinge, Felix Ott
Image and Video Processing
NGPS: Structure-Preserving Self-Supervised Denoising via Neighbor-Guided Patch Sampling
Jaehyun Cho and YoungJoon Yoo
Neighboring-slice self-supervised denoising is attractive for volumetric medical imaging, yet inter-slice misalignment breaks anatomical correspondence and often yields ghosting and blurred margins when adjacent slices are used naively as targets. We propose Neighbor-Guided Patch Sampling (NGPS), a lightweight framework that constructs neighboring supervision under local inter-slice misalignment without explicit registration. To avoid learning from misleading targets, prior methods commonly mask discrepant regions, but this stabilizes training at the cost of leaving a non-trivial portion of neighboring evidence unexploited, particularly around high-frequency anatomical boundaries. NGPS addresses this by decoupling structure matching from signal
retrieval: for each masked location, it searches a local neighborhood for structurally similar candidate patches using a simple guide image (e.g., fast bilateral filtering), while retrieving the supervision signal directly from the raw noisy neighbor at the matched coordinates. By matching on a noise-attenuated guide while retrieving raw values from neighboring slices, NGPS constructs local pseudo targets without a learned registration module. Across the evaluated CT and synthetic-Rician MRI settings, NGPS improves fidelity and structure-sensitive metrics. Code is available at https://github.com/cv-cho/NGPS .
Read the full abstract ▾
Audio and Speech Processing
FlowTTS-GRPO: Online Reinforcement Learning with Multi-Objective Reward Optimization for Flow-Matching Based Text-to-Speech
Haoxu Wang, Biao Tian, Weiqin Li et al. (+3 more)
Existing Reinforcement Learning (RL) research for Text-to-
Speech (TTS) focuses on large
language models (LLMs), leaving Flow-Matching (FM) under-explored. We present FlowTTS-GRPO, an online RL framework for FM-based TTS. By converting ordinary differential equation (ODE) trajectories into
stochastic differential equation (SDE) paths, our method enables direct fine-tuning of open-source FM models without auxiliary models. We show that a weighted reward combination converges faster than a probabilistic scheme, and identify three practical optimizations: omitting classifier-free guidance (CFG) during training accelerates convergence; synthesizing hard cases improves robustness; and applying RL to the FM component enhances audio-detail metrics. Experiments on CosyVoice 3.0 and F5-TTS demonstrate objective and subjective preference gains in speaker similarity and perceptual quality, with F5-TTS also improving intelligibility.
Read the full abstract ▾
All authors Haoxu Wang, Biao Tian, Weiqin Li, Xiang Lv, Han Zhao, Xiangang Li
Signal Processing
Phase Uniformity Detector for GRSMReceivers in mmWave and Sub-THz Bands
Oshin Daoud, Haifa Fares, Yahia Medjahdi et al. (+2 more)
This paper introduces a phase-domain statistical detector, the Phase Uniformity Detector (PUD), for binary hypothesis testing in Generalized Receive Spatial Modulation (GRSM) systems. The PUD uses direct RF sampling to obtain received signal samples, their phases are modeled via Directional Statistics (DS). A Generalized Likelihood Ratio Test (GLRT) is derived and reduced to a Rayleigh uniformity test with a closed-form, noise-variance-independent threshold. Unlike conventional Energy Detection (ED), the PUD offers robust spatial detection under Independent Local Oscillator Phase Noise (ILO-PN), remaining insensitive to energy fluctuations and noise uncertainty. Additionally, a phase-coherence-aware combining scheme mitigates ILO-PN without requiring estimation.
Read the full abstract ▾
All authors Oshin Daoud, Haifa Fares, Yahia Medjahdi, Laurent Clavier, Amor Nafkha
Image and Video Processing
A Benchmark of (MRI-) Foundation Models to Predict IDH Mutational Status in Glioma
Nathan Hollet, Elise Robinson, Efthymios Georgiou et al. (+3 more)
Non-invasive prediction of glioma molecular status from routine
magnetic resonance imaging (MRI) has shown promising performance, but model generalization remains challenging given small-scale matched imaging-genomic
datasets. Foundation models may address this bottleneck, but a comprehensive
benchmark is needed to establish the impact of diverse architectures, pre-training domains, and objectives. Given the use case of isocitrate dehydrogenase (IDH) mutation prediction from FLAIR and post-contrast T1 MRIs, we compared four image-based foundation models, BrainIAC, MRI-CORE, BiomedCLIP, and BrainDINO, against radiomics-based TabPFN and logistic regression baselines. Prediction performance and calibration were assessed across four public adult glioma cohorts and an external post-treatment cohort. Within-cohort, TabPFN matched or outperformed all visual encoders, achieving 0.92 (0.03) AUROC and 0.74 (0.17) AUPRC (mean (SD) across all
datasets). Among visual encoders, BiomedCLIP performed best (0.85 (0.08) AUROC), with BrainDINO competitive (0.82 (0.09) AUROC), while MRI-specific encoders (BrainIAC, MRI-CORE) consistently underperformed. Cross-cohort transfer showed moderate AUROC degradation but stronger AUPRC sensitivity to prevalence shifts. On the external cohort, BiomedCLIP achieved the highest AUROC (0.74 (0.07)), whereas TabPFN provided superior calibration (Expected Calibration Error 0.07 (0.01)). These results indicate that representation modality and evaluation context critically influence foundation-model performance in MRI-based molecular prediction. Tabular foundation models on radiomic features provide a strong, well-calibrated baseline, while image foundation models may offer complementary value under clinically distinct distribution shifts. Code available at https://github.com/nathanhollet/idh-status-prediction
Read the full abstract ▾
All authors Nathan Hollet, Elise Robinson, Efthymios Georgiou, Ekin Ermis, Uri Nahum, Sarah Brüningk
Signal Processing · Cross-listed from cs.IT
Movable Antennas for Robust Wireless Sensing via Joint Cramér-Rao Bound and Sidelobe Minimization
Wenyan Ma, Lipeng Zhu, Weitong Zhai et al. (+1 more)
This paper presents a novel design approach for movable
antenna (MA)-enabled wireless sensing systems by jointly minimizing the Cramér-Rao bound (CRB) and the maximum sidelobe level (MSL) of the ambiguity function via
antenna position optimization. In particular, the mean squared error (MSE) of angle-of-arrival (AoA) estimation is decomposed into a local estimation error within the mainlobe of the ambiguity function (i.e., CRB) and an additional ambiguity error caused by its sidelobes. Since the MSE is dominated by the CRB in the high-signal-to-noise ratio (SNR) regime but by the sidelobes of the ambiguity function in the low-SNR regime, our analysis reveals a fundamental trade-off between CRB minimization and MSL minimization in the moderate-SNR regime. Specifically, minimizing the CRB prefers a narrower mainlobe, where
antennas are concentrated near the two edges of the one-dimensional (1-D) movement region; whereas minimizing the MSL favors a wider mainlobe, where
antennas are distributed more densely near the center of the movement region. Inspired by this and to ensure robust sensing performance across different SNR regimes, we formulate an optimization problem to minimize the CRB subject to a prescribed MSL constraint via
antenna position optimization. An efficient successive convex approximation (SCA)
algorithm is developed to optimize the
antenna position vector (APV), and a 1-D linear search method is proposed to determine the optimal MSL threshold that minimizes the actual MSE for any given SNR. Numerical results demonstrate that the proposed scheme effectively balances the trade-off between MSL and CRB minimization, thus achieving a significantly lower AoA estimation MSE across the entire SNR range compared to conventional uniform and non-uniform fixed-position
antenna (FPA) arrays.
Read the full abstract ▾
All authors Wenyan Ma, Lipeng Zhu, Weitong Zhai, Rui Zhang
Signal Processing
When Distortion Helps: Secure GNN Precoding with Nonlinear Power Amplifiers
Reza Ghasemi Alavicheh, Thomas Feys, Md Arifur Rahman et al. (+1 more)
Physical layer security (PLS) provides information-theoretic protection against eavesdropping. While existing techniques assume ideal linear transmitters, power amplifiers (PAs) in practice introduce nonlinear distortion, typically considered detrimental to signal quality. This paper demonstrates that such distortion can instead be exploited as a security asset by redirecting it toward eavesdroppers, particularly in the power-efficient PA saturation regime. To this end, we propose a graph neural network (GNN)-based precoding framework for multi-user multiple-input single-output (MISO) wiretap channels that maximizes the sum secrecy rate by exploiting PA nonlinearity. Since the resulting optimization is highly non-convex, classical methods are intractable. The GNN instead learns precoding strategies directly from legitimate users' channel data, requiring neither eavesdropper channel state information (CSI) nor dedicated artificial noise (AN) power allocation. For this, the Bussgang decomposition and a high-order
polynomial PA model provide an analytical secrecy rate as the training objective. At 22 dB signal-to-noise ratio (SNR) under severe PA saturation with input back-off (IBO) $= -1$ dB, the proposed GNN achieves 39.89% and 35.26% higher sum secrecy rate over maximum ratio transmission (MRT) and zero-forcing (ZF), respectively, 17.99% over AN-aided MRT and 8.67% over AN-aided ZF, with 58.13-75.31% lower standard deviation across all baselines.
Read the full abstract ▾
All authors Reza Ghasemi Alavicheh, Thomas Feys, Md Arifur Rahman, François Rottenberg
Audio and Speech Processing
Audio Editing in the Era of Foundation Models: A Survey
Changhao Pan, Yifei Fan, Fan Zhuo et al. (+13 more)
Audio editing aims to modify a given synthetic or real-world audio signal to satisfy specific user needs. As a promising yet challenging direction in AIGC, it has attracted increasing
attention. Recent advances in audio generation have made powerful generative models central to modern audio editing systems. This rapid progress has created a growing need to organize emerging tasks, methods, and resources into a coherent view. In this survey, we provide a comprehensive review of audio editing in the era of foundation models. We first present a unified taxonomy of existing editing tasks and then summarize the major foundation-model paradigms that support modern audio editing, covering representative approaches from both training-based and training-free perspectives. We further discuss related resources, including
datasets, evaluation protocols, and data construction tools. Finally, we identify open challenges in this field and outline promising directions for future research. The project page is released at https://github.com/DaViD-Pigeon/AudioEditSurvey.
Read the full abstract ▾
All authors Changhao Pan, Yifei Fan, Fan Zhuo, Yifu Chen, Wenxiang Guo, Yu Zhang, Ruiqi Li, Zhiyuan Zhu, Rui Yang, Shengpeng Ji, Chenyuhao Wen, Jiayang Xu, Ke Lei, Xiaoda Yang, Jingyu Lu, Zhou Zhao
Signal Processing
AI-Empowered UAV-Assisted Backscatter Localization and ISAC for Zero-Energy IoT: A Comprehensive Survey
Ruhul Amin Khalil
Zero-energy Internet of Things (IoT) enables passive or near-passive devices to operate on harvested energy rather than batteries. Backscatter communication (BackCom) supports this
vision by enabling tags to transmit data via reflection and modulation of incident RF signals, but it suffers from weak reflections, double-path loss, limited coverage, direct-link interference, and dependence on external RF sources. Unmanned aerial vehicles (
UAVs) can mitigate these limitations by acting as mobile carrier emitters, data collectors, relays, aerial receivers, mobile anchors, sensing platforms, and edge-intelligence nodes. Integrated sensing and communication (
ISAC) further enables the sharing of wireless resources for data transmission, localization, target sensing, and environmental awareness. This article surveys RF-based AI-empowered
UAV-assisted backscatter localization and
ISAC for zero-energy IoT. It reviews enabling technologies, presents a structured PRISMA-informed methodology, and develops a unified taxonomy covering network architectures,
UAV roles, backscatter modes, RF sources, localization and sensing functions, AI techniques, and performance metrics. It also discusses
UAV-assisted BackCom, passive localization,
ISAC-enabled
UAV-backscatter systems, and AI-driven optimization through comparative tables, quantitative trend analysis, coverage evaluation, and tutorial-style numerical illustrations. Finally, it identifies open challenges and future directions in realistic channel modeling, energy-neutral operation, benchmarking, reproducibility, scalable and trustworthy AI, security,
privacy, hardware validation, and integration with RIS, MEC, digital twins, and 6G technologies.
Read the full abstract ▾
Signal Processing
Fault Inception Detection in Real-World Disturbance Data for Power System Protection
Julian Oelhaf, Mehran Pashaei, Paula Andrea Perez-Toro et al. (+5 more)
Large collections of real-world disturbance recordings are increasingly available in transmission networks, but their value for power system protection and automated disturbance analysis is limited by the absence of precise event-onset annotations. In practice, field-recorded voltage and current waveforms contain switching operations,
transformer energization, resonance, saturation, and other non-ideal effects that can obscure or mimic genuine fault signatures, making reliable fault inception detection difficult. This paper presents an training-free framework for fault inception detection in real-world transmission disturbance data. The method combines protection-domain indicators, robust median/MAD-based normalization, a low-latency transient path, and persistence-aware fusion and veto logic to distinguish fault-consistent disturbances from non-fault transients. We apply the framework to 12053 transmission-level recordings from the publicly available RTE database and further assess detector performance on a manually reviewed subset of 300 events. On the reviewed subset, the detector achieves 96.6% recall, 79.2% precision, and a median timing error of 4.2ms for matched detections. These results indicate that the proposed approach can support protection-oriented disturbance screening, relay and post-event analysis, and the creation of timestamp annotations for downstream data-driven monitoring tasks.
Read the full abstract ▾
All authors Julian Oelhaf, Mehran Pashaei, Paula Andrea Perez-Toro, Georg Kordowich, Christian Bergler, Andreas Maier, Johann Jaeger, Siming Bayer
Signal Processing
LOLLA: Deep Reinforcement Learning for Closed-Loop Link Adaptation Towards a GPU-Accelerated AI-RAN
Rui Wang, Linchao Zhang, Qiang Liu et al. (+1 more)
Outer-loop link adaptation (OLLA) is widely deployed in 5G NR to track channel variations, yet its reliance on first-order, single-bit feedback degrades performance significantly under high-mobility and fast-varying channels. This paper presents LOLLA (Learned Outer-Loop Link Adaptation), a deep reinforcement learning framework that replaces the conventional OLLA staircase with a learned, continuous SINR offset conditioned on rich PHY/MAC telemetry inaccessible to OLLA. The offset modulates the SINR-to-MCS lookup table, preserving 3GPP-compliant MCS selection and provably subsuming the conventional OLLA update rule. A Proximal Policy Optimization (PPO) policy trained under a Lagrangian block error rate (BLER) constraint automatically enforces tunable reliability targets from 1% to 15% without manual penalty calibration. The framework is realized as the first closed-loop AI-native control dApp on a GPU-accelerated 5G NR stack, achieving end-to-end control latencies under 500 microseconds. Evaluations under 3GPP TDL channel models demonstrate 15% to 92% throughput gains over OLLA across Doppler frequencies up to 400 Hz, while attaining a Pareto frontier that strictly dominates OLLA across all evaluated reliability targets. The learned policy generalizes to unseen channel models and scales to eight concurrent UEs under shared-resource scheduling. In the uplink formulation, the gNB directly observes decoding outcomes, enabling simulation-to-deployment parity.
Read the full abstract ▾
All authors Rui Wang, Linchao Zhang, Qiang Liu, Kun Yang
Audio and Speech Processing
AudioCALM: Continuous Autoregressive Language Modeling for Universal Audio Generation
Huadai Liu, Kaicheng Luo, Wen Wang et al. (+4 more)
Unifying
speech, sound, and music generation in one model is hindered by tradeoffs between fidelity, end-to-end training, in-context conditioning, and variable-length synthesis that no current paradigm fully resolves. To address this challenge, we present AudioCALM, a universal audio generation framework that extends autoregressive (AR) next-
token prediction from discrete
tokens to continuous audio latents: a thin flow-matching head replaces the softmax to predict rectified-flow velocities at each position, and a block-causal AR-Flow
attention pattern produces arbitrary-length output. Joint training of multiple audio generation tasks faces an asymmetric text–audio mismatch:
speech transcripts align to specific time spans and demand tight, time-aligned
attention, whereas sound and music captions describe only overall semantics and rely on diffuse, holistic
attention; mixing the two disproportionately degrades sound and music generation. We address this asymmetry at two levels: a data reformulation strategy that unifies all three tasks under a single description-style conditioning interface, and a novel architecture Asymmetric Mixture-of-Modality-Experts (A-MoME), which adds a dedicated residual expert for
speech while sound and music share the backbone, incurring no inference overhead on non-
speech inputs. Experimental results demonstrate that AudioCALM matches modality-specific state-of-the-art and outperforms prior unified baselines on
speech, sound, and music generation
benchmarks.
Read the full abstract ▾
All authors Huadai Liu, Kaicheng Luo, Wen Wang, Qian Chen, Bin Ma, Xiangang Li, Wei Xue