Audio and Speech Processing
A Hybrid Classical-Learning Framework for Adaptive Decision Directed Speech Enhancement
Ali Rajabi and Xiangwei Zhou
Speech enhancement aims to recover clean
speech signals from noisy observations while preserving
speech quality and intelligibility. Classical methods such as Spectral Subtraction and Decision-Directed (DD) enhancement remain widely used because of their interpretability and low computational complexity, but they may suffer from musical-noise artifacts or excessive attenuation of weak
speech components under low signal-to-noise ratio (SNR) conditions. This paper proposes an Adaptive Beta-Constrained Decision-Directed (ABCDD)
speech enhancement framework that extends the conventional DD method through a frame-dependent lower gain bound. The introduced beta parameter controls the tradeoff between noise suppression and
speech preservation. To automate parameter selection for large and diverse
datasets, a lightweight multilayer perceptron (MLP) model is further developed to predict frame-level beta values directly from noisy-
speech features. The proposed framework is evaluated using both a representative
speech example and large-scale testing on the VoiceBank-DEMAND
dataset. In the representative example, ABCDD outperformed conventional Spectral Subtraction and classical DD across multiple objective metrics, including SNR, Log-Spectral Distance (LSD), Root-Mean-Square Error (RMSE), correlation, and Scale-Invariant Signal-to-Distortion Ratio (SI-SDR). On 100 unseen VoiceBank-DEMAND test files, the proposed MLP-beta ABCDD method improved average scale-aligned SNR from 9.41 dB to 13.82 dB, corresponding to an average gain of 4.41 dB. The results indicate that combining interpretable classical enhancement structure with lightweight machine-learning-based parameter adaptation provides an effective and practical direction for robust
speech enhancement.
Read the full abstract ▾
Signal Processing
Beyond the Raw Waveform: Fusing Visual Representations of EDA for Stress Detection
Stefanos Gkikas, Thomas Kassiotis, Yang Guo et al. (+5 more)
Electrodermal activity (EDA) is widely used in automatic stress detection, yet most pipelines treat it only as a raw one-dimensional waveform. This study examines whether complementary visual representations of EDA provide useful information for stress classification and whether their fusion im- proves recognition performance. Six image-based representations are derived from each EDA recording: an unwrapped short-time
Fourier transform (STFT) phase spectrogram, an instantaneous-frequency map computed from that phase, a power spectral density (PSD) spectrogram, a continuous wavelet transform scalogram, a recurrence plot, and a rendered waveform trace. The selected representations are stacked as channels of a single multichannel input, together with the raw waveform, and processed by a shared asymmetric-
attention architecture. Experiments on a 58-subject stress
dataset show that representation fusion improves over the raw waveform. The best configuration, which combines five representations while excluding the unwrapped phase spectrogram, reaches 70.97% test accuracy, compared with 67.36% for the raw waveform. The single PSD spectrogram achieves 69.44%, remaining close to the best-fused configuration at a lower computational cost. The results show that alternative visual forms of the same EDA signal can provide useful inductive biases for stress detection, and that a compact selection of complementary representations can be more effective than the raw waveform alone.
Read the full abstract ▾
All authors Stefanos Gkikas, Thomas Kassiotis, Yang Guo, Guangliang Li, Eric Nichols, Houshyar Asadi, Nikolaos Smyrnis, Giorgos Giannakakis
Image and Video Processing
Decodable but Not Accessible: Auditing Distance-Based Reliability Estimation on Disentangled Skin-Lesion Representations
Duc-Vinh Tran
Distance-based reliability estimation assumes that a representation's geometry reflects its trustworthiness, yet this assumption is rarely tested under training interventions that reshape geometry directly. We audit this assumption under domain-
adversarial representation learning using a disentanglement dose-response ladder. Three checkpoint families share the same architecture and a 16-dimensional representation, differing only in orthogonality strength (lambda = 0, 1, 5). Representation geometry changed substantially with disentanglement strength: the condition number shifted by two orders of magnitude (Kendall tau = 0.84, exact p = 2.8e-5). This change was not accompanied by improved reliability estimation: Mahalanobis-distance AUROC (ISIC-test vs. PAD-UFES) remained flat and below chance (about 0.40) at every level, with no significant association with any of five geometry metrics tested. The same failure was observed for cosine-to-centroid and pooled k-nearest-neighbor scorers, plus three non-distance-based scorers: an energy-based confidence score, Virtual-Logit Matching, and a kernel density
estimator. Seven of eight scorers converged on the same result; the energy-based score showed an isolated upward trend that we report but do not treat as evidence against the overall pattern. A supervised probe with no access to the training objective recovered domain membership from the identical
embeddings at 0.72-0.81 AUROC across every level, showing that the relevant information was not absent from the representation. These findings indicate that classification performance alone can overlook whether information in a learned representation is organized in a form that downstream reliability
estimators can use. Information can remain decodable while becoming largely inaccessible to non-probing reliability
estimators.
Read the full abstract ▾
Audio and Speech Processing
In Defense of Using Worst-case Privacy Disclosure as Privacy Evaluation Metric of Voice Anonymization
Xin Wang and Xiaoxiao Miao
The voice anonymization community mainly uses Equal Error Rate (EER) to evaluate the performance of voice identity protection. While alternative metrics such as
privacy-ZEBRA and a rank-based metric have been proposed, their underlying assumptions and differences may not be well known, especially to newcomers. This paper is motivated to fill the gap. Based on the concept of Shannon's perfect secrecy (or
privacy), this paper positions itself as a defense of the
privacy-ZEBRA framework. While no new metric is proposed, this paper explains how an `ideal' system in terms of EER may fail to gauge the information leakage on individual speakers in the log-likelihood ratio (LLR) space. The paper also shows how the rank-based metric can be cast into a metric that follows the same principle of perfect secrecy and how their best solutions are equivalent. Furthermore, the paper explains how the method of estimating LLRs may affect the evaluation results. These discussions are, to the best of the authors' knowledge, not explored or explained in detail in existing papers. Last but not least, the findings are demonstrated on simulated and VoicePrivacy Challenge data.
Read the full abstract ▾
Systems and Control
Switching Observers for Linear Systems: Beyond Individual Observability
Masoud S. Sakha and Rushikesh Kamalapurkar
This paper develops an LMI-based switching observer for linear time-invariant systems with two output channels, where only one output is available at any given time. We assume that the system is observable when both outputs are considered together, and that the time intervals between consecutive output switches are uniformly bounded. Under these assumptions, we design a set of channel-dependent Luenberger observer gains offline via linear
matrix inequalities and show that the resulting switched observer drives the estimation error to zero. The main contribution is an offline gain design and convergence result for switched observers that does not require individual output channels to be detectable.
Read the full abstract ▾
Image and Video Processing
BreastMammo and DenseMammo: Benchmarks for Mammography Domain Generalization
Hongyi Pan, Gorkem Durak, Halil Ertugrul Aktas et al. (+18 more)
Breast density classification is a critical component of breast cancer risk assessment, yet AI models often struggle to generalize across clinical sites due to vendor-specific acquisition styles. In this work, we introduce two new
datasets, BreastMammo and DenseMammo, to facilitate robust multi-view mammography research. We propose a domain generalization framework that utilizes a foreground-only histogram matching protocol to resolve the domain shift issue arising from disparate clinical sources. Internal evaluation using a 5-fold cross-validation protocol demonstrates the efficacy of our approach, with the Swin
Transformer backbone achieving a peak AUC of 98.32% for density classification. External evaluation on the TNMammo and LUMINA
datasets demonstrates that the proposed approach consistently reduces domain shift, significantly outperforming prominent domain generalization paradigms, including MixStyle and Discrete-
Fourier-Transform-based frameworks.
Read the full abstract ▾
All authors Hongyi Pan, Gorkem Durak, Halil Ertugrul Aktas, Andrea Mia Bejar, Mustafa Ege Seker, Nebile Alibeyoglu, Rumeysa Guclu, Rana Gunoz Comert Bozkurt, Sibel Ozkan Gurdal, Neslihan Cabioglu, Beyza Ozcinar, Ravza Yilmaz, Vahit Ozmen, Erkin Aribal, Sukru Mehmet Erturk, Yalda Zafari, Mohamed Mabrok, Kayhan Batmanghelich, Mohammad Yaqub, Ziyue Xu, Ulas Bagci
Signal Processing
Achievable Accuracy and Cramer Rao Bounds for SSB Based LEO Positioning in NR NTN
Rainer Bachl, Tingting Lei and Muhammad Nabeel
Advanced Low Earth Orbit (LEO) satellite networks, such as Starlinks Mobile Satellite Service (MSS), will adopt the 5G New
Radio (NR) Non-Terrestrial Network (NTN) standard. This enables the use of ubiquitous Synchronization Signal Blocks (SSBs) for opportunistic receiver positioning based on pseudorange and Doppler measurements. In this work, we characterize the estimation theoretic limits of SSB-based positioning by deriving single SSB Cramer Rao lower bounds (CRLBs) for delay and carrier frequency observables associated with pseudorange and Doppler. These bounds are obtained using the full SSB time-frequency energy distribution and extended into a multi epoch, multi satellite Fisher information framework that jointly bounds stationary user position, clock bias, and clock drift. Each SSB contribution is weighted according to a range dependent CRLB determined by the received SNR, so the
estimator and the bound share a common noise model. In simulation, the resulting bound closely matches achievable performance, and a physically weighted least squares
estimator approaches the CRLB at realistic operating SNR. Using a Starlink based constellation, we analyze the operating SNR experienced by a ground user and demonstrate sub-meter positioning accuracy.
Read the full abstract ▾
Systems and Control · Cross-listed from math.OC
Continuous-Time Covariance Steering with Common Free-Final Time: Finite-Horizon Solutions and Infinite-Horizon Limits
Akan Selim, Fengjiao Liu, Siddhartha Ganguly et al. (+1 more)
This article studies the optimal common free-final time problem for steering the state covariance of a continuous-time
stochastic linear system between prescribed initial and terminal covariance
matrices. We first establish a deterministic reformulation of the SDE-constrained free-final time
stochastic optimal control problem (SOCP). For the ensuing SOCP, we provide necessary conditions for optimality and establish sufficient conditions for the optimal common final time to be finite. Subsequently, we characterize the asymptotic behavior of the finite-horizon optimal solutions as the final time tends to infinity, the invariant sets and trajectories associated with this limiting regime, and derive the sensitivity of the
Hamiltonian with respect to the common final time. Finally, leveraging these sensitivities, we develop a trust-region line-search
algorithm together with an infinite-horizon case detection method, and demonstrate its performance on three different problems: (a) an illustrative covariance-steering example, (b) a demonstration of spacecraft maneuver using covariance control, and (c) Gaussian mixture to Gaussian mixture steering.
Read the full abstract ▾
All authors Akan Selim, Fengjiao Liu, Siddhartha Ganguly, Panagiotis Tsiotras
Systems and Control
A Pragmatic Guide to Building Conservative Discrete Abstractions of Cyber-Physical Systems
Jordan Peper, Krish Kapadia, James Gast et al. (+2 more)
Symbolic model checking is an effective approach for verifying semantically rich temporal-logic properties of cyber-physical systems, but it hinges on discretizing continuous-state dynamics into a finite-state abstraction. To transfer verification guarantees from the abstract model to the concrete CPS, the abstraction must conservatively approximate the concrete state space and behaviors. Hence, model-builders must maintain this soundness while balancing pessimism with tractability. However, they face several common pitfalls such as under-approximating the state space, under-approximating transitions, unsound
pruning of "degenerate" behaviors, and improper specification lifting. This tutorial presents a pragmatic, conservative-by-construction workflow for building discrete abstractions of closed-loop dynamical systems. The workflow consists of four modular steps with interchangeable subroutines: (i) state-space partition and abstraction-function design, (ii) conservative transition construction via axis-aligned bounding boxes, polytopes, or sampling with PAC coverage certificates, (iii) mitigation of spurious transitions and self-loops using certified erasure and counterexample-guided abstraction refinement, and (iv) sound lifting of LTL specifications using may-must semantics. We demonstrate the end-to-end pipeline on three case studies and report how these design choices affect abstraction structure, runtime, and verification outcomes.
Read the full abstract ▾
All authors Jordan Peper, Krish Kapadia, James Gast, Ethan Howes, Ivan Ruchkin
Systems and Control · Cross-listed from math.OC
Towards Co-Designed Event-Triggered Extremum Seeking
Roberto Luo, Pedro Henrique Silva Coutinho, Victor Hugo Pereira Rodrigues et al. (+2 more)
This paper studies event-triggered gradient-based multivariable extremum seeking for nonlinear maps with polytopic Hessian uncertainty. Unlike existing event-triggered extremum-seeking methods, which first fix the controller (typically diagonal) and then design the triggering mechanism, the proposed approach jointly synthesizes the controller and the triggering mechanism through a co-design framework that admits both diagonal and full controller gain
matrices. The co-design problem is formulated as a convex optimization problem with linear
matrix inequality constraints. Its solution guarantees exponential convergence of the average closed-loop system with a prescribed decay rate while maximizing the admissible triggering threshold to reduce communication. Lyapunov and averaging analyses establish exponential stability of the event-triggered system, and Zeno-freeness is proved to guarantee implementability. Numerical results illustrate that diagonal gains cannot achieve the same triggering thresholds and decay rates as the full controller gain
matrices, highlighting the benefits of exploiting Hessian coupling information.
Read the full abstract ▾
All authors Roberto Luo, Pedro Henrique Silva Coutinho, Victor Hugo Pereira Rodrigues, Tiago Roux Oliveira, Miroslav Krstic
Signal Processing
A JEPA-Based Field-Layer World Model for Bridging Channel Prediction and Estimation
Yuzhi Yang, Brahim Mefgouda, Hang Zou et al. (+5 more)
Channel state information (CSI) acquisition, reconstruction, and prediction are fundamental yet costly tasks in modern
MIMO-OFDM wireless systems. Direct coefficient-level prediction of raw CSI is fragile in realistic propagation environments, since small spatial perturbations, local scattering changes, and phase variations can cause large errors in the complex channel domain. However, the underlying wireless propagation field still contains stable and predictable structures that can be exploited across time, frequency,
antenna, and carrier dimensions. Motivated by this observation, we propose a JEPA-based field-layer world model (FWM) that learns a shared latent propagation state from multi-resolution CSI observations across the considered carrier bands and predicts its task-relevant
evolution in the latent domain. The proposed FWM maps multiple CSI observation resolutions to a shared latent propagation-field space through scale-specific tokenizer heads. A latent prediction backbone is then trained to infer masked or future field states, while an incremental multi-scale
alignment strategy allows new observation scales to be incorporated without retraining the entire model from scratch. For downstream reconstruction, the predicted latent field is used as a structured prior and combined with sparse current pilots. Experiments on single-band and cross-band reconstruction demonstrate improved symbol detection and, more notably, substantial beamforming gains despite modest NMSE improvements, indicating that FWM captures task-relevant spatial propagation structure beyond coefficient-wise CSI fitting.
Read the full abstract ▾
All authors Yuzhi Yang, Brahim Mefgouda, Hang Zou, Lina Bariah, Anis Bara, Yuhuan Lu, Hao Zhang, MérouaneDebbah
Signal Processing
Transceiver Design for Cell-Free Unsourced Random Access
Mert Ozates, Mohammad Kazemi, Eduard Jorswieck et al. (+1 more)
We propose a low-complexity, energy-efficient solution for
cell-free unsourced random access (URA), in which multiple distributed access points are connected to a central processing unit via a fronthaul. Assuming that each user transmits a pilot sequence followed by a polar codeword whose symbols are placed to the data part of the frame according to an on-off pattern, we utilize iterative decoding, including orthogonal matching pursuit (OMP)-based pilot detection and channel estimation, symbol estimation using a linear minimum mean square error (MMSE) solution, symbol combining, single-user decoding, and successive interference cancellation (SIC). We also present finite blocklength (FBL) performance and detailed complexity analyses. Numerical results demonstrate that the FBL analysis properly characterizes system performance and that the proposed
cell-free URA scheme offers superior performance compared to existing low-complexity schemes. Namely, it offers a superior performance of up to 4.5 dB and can accommodate up to 1800 active users.
Read the full abstract ▾
All authors Mert Ozates, Mohammad Kazemi, Eduard Jorswieck, Deniz Gündüz
Systems and Control · Cross-listed from math.OC
A New Approach for Feedback Stabilization and its Application for Data-Driven Control of Polynomial Systems
Diego de S. Madeira, Joao Gabriel N. Silva, Wilkley B. Correia et al. (+1 more)
Inspired by recent developments in dissipativity-based control, this work proposes new sufficient conditions for asymptotic stabilization of nonlinear systems using state feedback. We prove that this new framework is well suited for data-driven control of
polynomial systems using noisy measurements, a topic that has lately attracted considerable
attention. Two iterative procedures for data-based state feedback design are provided using the proposed framework, that use sum-of-squares (SOS) optimization. Typical limitations of conventional SOS methods based on alternating (D-K) procedures for controller design, such as the need to provide an initialization for a control-Lyapunov function (CLF), are overcome in this paper. Numerical examples demonstrate the applicability and the advantages of the new strategies.
Read the full abstract ▾
All authors Diego de S. Madeira, Joao Gabriel N. Silva, Wilkley B. Correia, Antonis Papachristodoulou
Signal Processing
Pinching-Antenna Systems: From Antenna Placement to Antenna Roaming
Kaidi Wang, Daniel K. C. So and Zhiguo Ding
This paper investigates pinching-
antenna systems with finite
antenna movement speed, under which conventional
antenna placement is subject to non-negligible repositioning delay, resulting in a fundamental tradeoff between channel quality and effective transmission time. In this context,
antenna roaming is proposed as a novel operation mode, in which the
antenna moves continuously along the waveguide while simultaneously serving users. By incorporating communication and
antenna movement into the same transmission cycle, a unified cycle-duration framework is established to facilitate a fair comparison between
antenna placement and
antenna roaming. The sum-rate difference is then analytically derived, indicating that
antenna roaming avoids dedicated positioning overhead with a loss in channel quality due to spatial averaging. The corresponding sum rate maximization problems are formulated for the two operation modes. The continuous optimization problems are transformed into finite-state sequential decision problems and solved via dynamic programming (DP) based
algorithms. For
antenna roaming, the optimal unconstrained service-interval partition is analytically characterized, with each
antenna position assigned to the user achieving the highest instantaneous rate. Simulation results validate the theoretical analysis, demonstrate the performance advantage of
antenna roaming over
antenna placement, especially when positioning overhead is significant, and confirm the effectiveness of the DP based solutions in improving the achievable sum rate.
Read the full abstract ▾
Systems and Control
Complexity of Local Observation Consistency in Discrete-Event Systems
Tomáš Masopust
Hierarchical and multi-
agent supervisory control under partial observation relies on local consistency conditions between a plant and its abstraction: local observation consistency (LOC) for the projection abstractions of hierarchical control, and local relabeling observation consistency (LROC) for the relabeling abstractions of multi-
agent systems. Both are companions to a global condition and both have been used without their verification complexity being settled. We show that both are PSpace-complete for nondeterministic plants and decidable in
polynomial time for deterministic plants.
Read the full abstract ▾
Audio and Speech Processing
BiTSE: Binaural Target Speaker Extraction in Noisy Multi-Talker Environments for AR Glass Arrays
Selani A. Indrapala and Wageesha N. Manamperi
Isolating a desired
speech signal in noisy multi-talker conversational scenarios is a key requirement for augmented reality (AR) wearable microphone array systems. In this work, a binaural target speaker extraction (TSE) framework, termed BiTSE, is proposed. It leverages both spatial and temporal cues, specifically the direction-of-arrival (DoA) of the target speaker and corresponding voice activity information, to guide the extraction process. Built upon a binaural signal denoising architecture, our model integrates three key enhancements: (i) a DoA-aware
attention mechanism using cyclic positional
embeddings, (ii) a timestamp-based masking strategy that utilizes speaker activity to suppress non-target segments, and (iii) a novel two-stage loss optimization strategy that first trains the model for robust denoising and then fine-tunes it to improve perceptual quality. Evaluations on the
SPeech Enhancement for Augmented Reality (SPEAR) challenge
dataset demonstrate that the proposed BiTSE consistently improves upon conventional approaches, leading to enhanced signal fidelity and perceptual quality.
Read the full abstract ▾
Systems and Control · Cross-listed from cs.SE
Exploring Semantic Stability Across Reviews in the Linux Kernel
Lucas Ciziks, Paulo Meirelles and Marco Aurélio Gerosa
Code review is credited with substantially changing a patch's code between its first submission and the version that eventually lands. However, prior work typically studied only the final merged patch without comparing it to the first submission. We present a function-level measurement that tracks 10,117 trajectories (each function followed across the numbered revisions of one patch series) through the patch history of the Linux IIO subsystem, comparing similarity scores against unrelated function pairs as a baseline. A naive reading yields near-total similarity, but this is largely an artifact of composition: 75.3% of tracked trajectories are never textually modified between versions, contributing a trivial 100% similarity that inflates the headline. Restricting to the trajectories with a real edit, semantic purpose is still largely preserved (mean similarity 0.990 vs. a 0.909 baseline), but drift appears to concentrate in the first review round mainly because later rounds contain more functions that nobody touched, not because edits become more conservative over time. After controlling for it, a statistically detectable but small residual effect remains. This points to an open question: whether near-ceiling similarity reflects preserved purpose or a measurement tool that cannot detect the significance of small, localized edits. We present this work as a first look and outline next steps.
Read the full abstract ▾
Image and Video Processing
When Repository Labels Are Not Image-Level Truth: A Supervision Auditing Framework for Chest Radiograph AI
Yesika Alexandra Agudelo-Londoño, Jhon Wilmer Pino-Román, Brahian Carrera Rodríguez et al. (+9 more)
Public chest X-ray repositories are widely used to train medical AI systems, yet their labels are typically extracted from radiology reports rather than verified directly on images. As a result, repository labels are often treated as image-level ground truth without validating whether they reflect what is actually visible in the radiograph. We introduce Repository Supervision Auditing (RSA), a framework that evaluates repository-derived labels against expert image-level annotations before model development. Using cardiomegaly in MIMIC-CXR as a case study, RSA compares repository labels with radiologist-reviewed image annotations, characterizes disagreement sources, and builds a curated cohort for deployment-oriented evaluation. Repository-derived cardiomegaly labels showed near-zero agreement with expert image-level assessment, identifying only 1% of expert-confirmed cases. Most discrepancies resulted from non-mention rather than explicit report negation, with expert-confirmed cardiomegaly identified in nearly half of studies assigned a repository-derived No Finding label. Using the resulting expert-curated cohort, a DenseNet121 model achieved a test ROC-AUC of 0.853. These findings show that repository labels may not reliably represent image-level truth and highlight supervision auditing as a critical step for developing trustworthy medical imaging AI.
Read the full abstract ▾
All authors Yesika Alexandra Agudelo-Londoño, Jhon Wilmer Pino-Román, Brahian Carrera Rodríguez, José Miguel Castañeda-Bedoya, Juan Pablo Gómez-López, Aura C. Puche-Sarmiento, Niharika S. D'Souza, Juan Sebastian Osorio-Valencia, Jon E. Duque-Grajales, Jazmín Ximena Suárez-Revelo, Jorge Mario Vélez-Arango, Gabriel Castrillón
Systems and Control · Cross-listed from cs.RO
Navigating the Proximity-Safety Balance: Constraint Decomposition for Human Following in Pedestrian Crowds
Shiting Gong, Jianpeng Yao, Jinfeng Wang et al. (+2 more)
Following a target human in crowded environments involves an inherent conflict between staying close to the target and navigating safely among surrounding pedestrians and obstacles. This conflict becomes more severe in dense scenarios, where aggressive following risks collisions and conservative margins lead to target loss, especially when pedestrian behaviors are unfamiliar or unpredictable. Existing reinforcement learning (RL) methods typically encode these competing objectives into a single dense reward, but the resulting proximity-safety balance is implicit and difficult to adjust across conditions. To address this, we decompose the human-following task into a sparse task reward and independent cost constraints within a multi-constraint RL formulation, where each constraint is managed through cost thresholds with direct behavioral meaning rather than implicit reward weight ratios, allowing explicit and tunable control over the trade-off. We further quantify the prediction uncertainty of human motions and integrate these estimates into the RL costs to enhance safety under unpredictable conditions. Extensive experiments across both in-distribution and out-of-distribution settings demonstrate that our method achieves an effective proximity-safety balance compared to baselines. Real-
robot deployment further validates the feasibility of our method in real-world scenarios. More details are available on our project page: https://nav-ps-balance.github.io/.
Read the full abstract ▾
All authors Shiting Gong, Jianpeng Yao, Jinfeng Wang, Marco Pavone, Jiachen Li
Audio and Speech Processing · Cross-listed from cs.SD
Training Set Synthesis for Bioacoustic Denoising: A Case Study With Mice
Reyhaneh Abbasi, Peter Balazs, Vincent Lostanlen et al. (+4 more)
Bioacoustic recordings are often degraded by ambient noise, which complicates the analysis of weak or noise-overlapped vocalizations. Convolutional neural networks, particularly U-Net architectures, have shown a strong denoising performance in
speech and music processing. However, their direct application to bioacoustic signals is limited by the scarcity of clean training data. To address this issue, we propose a training set synthesis approach and develop a supervised denoising model that predicts a complex ratio mask in the time-frequency domain. The model leverages ridges, or frequency contours, that represent the fundamental frequency together with one or more harmonic partial components of vocalizations. These ridges are used both for the synthesis of training sets and to design a loss function that assigns higher weights to the ridge regions (ridge-guided loss function). This weighting step helps the network better preserve vocalization details during denoising. As a case study, we evaluate our approach using ultrasonic vocalizations (USVs) recordings of house mice, which are widely studied in behavioral biology and neuroscience. In actual field recordings, the proposed method enhances fundamental and harmonic partial ridge tracking compared to our previous signal-processing approach. In addition, a classifier trained on denoised data improves USV classification on out-of-sample, noisy recordings from wild and domesticated mice compared to classifiers trained on noisy recordings. Our proposed method also substantially improves the scale-invariant signal-to-distortion ratio on synthetic testing data across a wide range of input signal-to-noise ratios. Although we focus on USVs, the proposed approach should be broadly applicable to other bioacoustic signals with trackable ridges, and thus enables ridgebased training set synthesis and denoising.
Read the full abstract ▾
All authors Reyhaneh Abbasi, Peter Balazs, Vincent Lostanlen, Clara Hollomey, Dustin J. Penn, Sarah M. Zala, Nicki Holighaus
Signal Processing
Unrolling a Graph-Laplacian Denoiser Realizes Only Compositions of Polynomial Graph Filters
Seyed Alireza Hosseini
A recent construction of unrolled networks for graph-based image restoration forms a system
matrix from a graph-
Laplacian denoiser through a truncated Taylor expansion, then inverts it with a fixed number of conjugate-gradient steps, with the coefficients of both stages learned. This paper shows the resulting map is a
polynomial in the denoising operator, of degree at most the product of the two truncation orders, for every setting of those coefficients and therefore at every point of training: the learned steps select an element of a Krylov subspace they cannot enlarge. At the orders used in practice the reachable set is moreover a measure-zero subset of the
polynomial class of the network's own degree budget, so the composition constrains the hypothesis space rather than enlarging it. At the standard initialization the realized spectral response is obtained in closed form, exceeding the intended response throughout the interior of the spectrum and approaching a nonzero floor. A lower bound on the operator's condition number, internal to the graph construction rather than to image content, then places the order required for a prescribed accuracy well above the order used in practice. The confining class is precisely the spectral graph filters for which a direct, convex parameterization has long been available.
Read the full abstract ▾
Signal Processing
Wavenumber-Domain Virtual Arrays for Holographic Near-Field Localization
Giovanni Iacovelli, Chandan Kumar Sheemar and Symeon Chatzinotas
Monostatic localization of multiple point targets is studied for a holographic aperture operated through wavenumber-domain modes. A specular-point condition delimits the validity of the spectral model as a near-field approximation. A single snapshot observes a projection of dimension at most the target count times the polarization components, while invertible coding recovers the full channel and places the decoded data on the difference
lattice of transmit and receive wavenumbers. Rank conditions settle identifiability, and the Fisher
matrix reduces to a covariance over the
lattice, dictating a nested mode selection that attains full-aperture resolution with only tens of RF chains.
Read the full abstract ▾
Signal Processing
An open-source, scalable workflow for organizing echosounder data for machine learning applications
Caesar Tuguinay, Wu-Jung Lee, Valentina Staneva et al. (+4 more)
Echosounders, or high-frequency active sonar systems, have become standard tools for quantifying and mapping the distribution of marine organisms in fisheries or ecological surveys. Conventional echosounder data analysis often relies on human annotation of echograms, which are sonar imagery formed by echo intensity. Over the past decade, in parallel with the exponentially growing volume of echosounder data, there has been a corresponding increase in the development of machine learning (ML) methods that operate primarily on echograms as images. However, echograms are not simply images: they are associated with specific spatiotemporal coordinates that are essential for
alignment with survey events, human annotations, and other oceanographic
datasets. We present a generalizable two-stage workflow for constructing analysis-ready
datasets for ML development tailored for echograms from transect-based surveys, in which (1) acoustic data are partitioned according to transect designation, and (2) masks are created from annotations referencing user-defined uniform spatiotemporal echo data grid. Importantly, ancillary information, such as geospatial coordinates and oceanographic measurements, is propagated across processing stages to preserve the essential contextual information for downstream analyses. We demonstrate the scalability of our workflow implementation based on two open-source software libraries, Echopype and Echoregions, using two example fisheries survey
datasets. We additionally provide an executable tutorial that guides readers through the computational implementation of this workflow. Together, these elements provide a scalable and generalizable framework for creating analysis-ready echosounder
datasets for ML applications.
Read the full abstract ▾
All authors Caesar Tuguinay, Wu-Jung Lee, Valentina Staneva, Elizabeth M. Phillips, Rebecca E. Thomas, Alicia Billings, Julia Clemons
Systems and Control · Cross-listed from cs.RO
WRAP: Wasserstein-Robust Adaptive Plug-in for Robot Localization
Minhyuk Jang, Astghik Hakobyan, Jungjin Lee et al. (+2 more)
Robotic localization under changing sensing conditions can suffer from biased errors and miscalibrated covariances. We present WRAP, an adapter-agnostic Wasserstein-robust plug-in for nonlinear extended Kalman filter (EKF) and error-state Kalman filter (ESKF) stacks. A causal module supplies time-varying effective process and measurement statistics; a mean-preserving Wasserstein local update then computes least-favorable covariances and a robust gain without changing the propagation model, residual, or retraction. This separates mean adaptation from covariance robustification and uses distinct radii for propagation and sensing. On 18 UWB–IMU sequences held out from adapter training, adapter-only and WRAP reduce mean 3-D position RMSE by $19.8\%$ and $27.4\%$ relative to the nominal ESKF; an isotropic ablation reaches $19.5\%$, linking the incremental gain to directional process-covariance redistribution. An in-sample GNSS–INS study shows that mean adaptation provides most of the accuracy gain, while DR improves consistency and mitigates over-tightened classical covariance estimates. The robust solve takes 0.05 ms for UWB and 2.92 ms for GNSS on a Jetson Orin Nano.
Read the full abstract ▾
All authors Minhyuk Jang, Astghik Hakobyan, Jungjin Lee, Naira Hovakimyan, Insoon Yang
Signal Processing
EEG-Based Characterization of Samatha and Vipassana Meditation States
M. A. B. C. A. Bandaranayake, K. P. U. Chandrathilake, J. L. S. Jayasekara et al. (+3 more)
Meditation has been associated with a range of cognitive and physiological benefits. However, the underlying neural mechanisms of different meditation practices are not yet fully understood. This study investigates whether electroencephalogram (
EEG) signals can be used to characterize and distinguish two commonly practiced meditation techniques, namely Samatha and Vipassana, which involve distinct cognitive processes, with Samatha emphasizing sustained concentration and Vipassana emphasizing mindful observation and insight. By extracting features such as band power, coherence and wavelet
entropy from
EEG signals recorded during pre-meditation resting, Samatha, and Vipassana states, we provide an assessment of how spectral power, signal complexity, and functional connectivity differentiate these practices. Preliminary results from $12$ experienced meditators indicate condition-dependent
EEG differences, with the most pronounced effects observed in the delta frequency band. These results demonstrate the utility of
EEG-based metrics for the objective characterization of meditation and advance our comprehension of the neural processes underlying different contemplative practices.
Read the full abstract ▾
All authors M. A. B. C. A. Bandaranayake, K. P. U. Chandrathilake, J. L. S. Jayasekara, S. T. Piyasena, A. T. L. K. Samrasinghe, Wageesha N. Manamperi
Image and Video Processing · Cross-listed from cs.CV
C$^2$A: Coupling Spatial Evidence with Clinical Priors via Co-occurrence Aware Class Attention for Multi-Label Chest X-Ray Classification
Akash Gogineni, Nagur Shareef Shaik, Aasrith Mandava et al. (+2 more)
Thoracic pathologies rarely occur in isolation, yet standard multi-label classifiers rely on shared global descriptors, discarding where findings lie and how they co-occur. We propose \textbf{C$\mathbf{^2}$A} (Co-occurrence Aware Class
Attention), a classification head that explicitly couples spatial evidence with clinical priors. First, C$^2$A casts pooling as an expectation over learned per-class spatial
attention maps, yielding localized descriptors for each disease. Second, it couples these descriptors via a learnable graph warm-started from empirical label co-occurrence. A single residual message-passing step shares evidence among related findings, proving to be a bounded perturbation of the identity where co-occurrence enters each logit through an explicit bilinear interaction. On CheXpert, C$^2$A achieves a superior $0.895$ macro-mean AUROC, outperforming advanced context-gating baselines. Crucially, gains concentrate on highly co-occurrent classes with ambiguous spatial evidence (rescuing Atelectasis by $+1.5$ over GCG), demonstrating the prior's regularizing effect with a negligible overhead of one linear projection and a $C\!\times\!C$ edge
matrix.
Read the full abstract ▾
All authors Akash Gogineni, Nagur Shareef Shaik, Aasrith Mandava, Adnan Masood, Dong Hye Ye
Audio and Speech Processing · Cross-listed from cs.CL
Structured Phonological Representations for Audio-Articulatory rtMRI Speech Classification
Abner Hernandez, Tomás Arias Vergara, Daiqi Liu et al. (+2 more)
Real-time MRI makes it possible to observe vocal-tract articulation during
speech, but mapping these articulatory patterns to phonetic and phonological categories remains challenging. We investigate whether PhonoQ, an audio-based model trained to recognize structured phonological features, provides useful information for audio–articulatory modeling. Specifically, we extract representations from PhonoQ's Conformer module, whose training is shaped by supervision for manner, place, voicing, and vowel features. Using articulatory contours with synchronized audio-derived features, we compare WavLM-large and HuBERT-large baselines with models that incorporate PhonoQ-derived representations. Across unseen-
speech and unseen-subject settings, these features improve macro-F1 for phonological targets including manner, place, voicing, vowel height, and vowel backness, and also improve fine-grained 39-phoneme classification. In a contour-only inference setting, audio-derived teacher supervision yields modest but consistent gains over contour-only training, indicating that phonological information from synchronized audio can be partially transferred to articulatory models. Finally, posterior analyses show interpretable surface-sensitive patterns consistent with flapping-like /t/ realizations, /t/-/r/ retraction or affrication, and nasal place assimilation.
Read the full abstract ▾
All authors Abner Hernandez, Tomás Arias Vergara, Daiqi Liu, Andreas Maier, Paula Andrea Pérez-Toro
Image and Video Processing · Cross-listed from cs.CV
Disentangling Co-Occurring Retinal Pathologies with Saliency-Guided Sparse Expert Routing
Nagur Shareef Shaik, Jeongwoo Park, Yeong-Jin Kim et al. (+3 more)
Retinal fundus images frequently exhibit multiple co-occurring pathologies, yet standard deep learning classifiers apply static, identical computation to every image regardless of the underlying disease distribution. We propose a novel architecture that resolves this via sparse conditional computation, pairing a Guided Context Gating (GCG) spatial
attention front-end with a sparsely-routed Mixture-of-Experts (MoE) block operating over feature
tokens. Crucially, this routing yields an interpretable, data-driven decomposition. Expert allocation is significantly disease-dependent (p < 0.001), with the healthy Normal state and morphologically distinct pathologies (e.g., ERM, AMD) isolating to dedicated experts. On a five-class, patient-disjoint 5-fold cross-validation
benchmark, our model achieves 0.912 +/- 0.008 macro AUC and 0.653 +/- 0.014 macro F1. Furthermore, Grad-CAM++ and post-MoE t-SNE visualizations confirm that expert routing aligns with localized lesions and geometrically maps co-occurring cases between their constituent clusters, positioning sparse MoE as an interpretable approach to multi-disease retinal screening.
Read the full abstract ▾
All authors Nagur Shareef Shaik, Jeongwoo Park, Yeong-Jin Kim, Jaeuk Jung, Hyunjung Oh, Dong Hye Ye
Systems and Control · Cross-listed from cs.DC
Defining Decentralization: An Ontological Perspective
Jakub Kacper Szeląg, Aydin Abadi and Mohammad Naseri
Decentralization as a concept in computer science has existed for over half a century. Despite its fundamental role across domains such as security, distributed computing, artificial intelligence, cloud infrastructures, and Internet of Things (IoT) architectures, there remains no universally accepted definition of decentralization applicable across computer communication systems. This has become increasingly problematic with the emergence of decentralized AI and machine learning paradigms, including collaborative training, distributed inference, blockchain-based, and agentic AI, where decentralization is often treated as a core design objective. Meanwhile, existing approaches frequently conflate decentralization with related notions such as distribution of trust or specific implementation paradigms. Such ambiguity creates inconsistencies in system analysis, limits comparability between works, and weakens the rigor of formal
reasoning surrounding communication architectures and protocol design. In this work, we define this research gap as the Decentralization Problem. We analyze the formal-semantic, epistemological, and pragmatic foundations of decentralization and introduce a graph-based ontology defining it as both relational and subject-specific property of computer communication systems. The framework formally distinguishes decentralization from distribution and supports evaluation through two novel metrics: Void Tolerance and Imperviousness. We also provide a browser-based implementation that enables automated classification and metric computation of arbitrary systems. Instantiations to
federated learning and blockchain architectures show consistent, comparable assessments where existing definitions produce incomplete or contradictory conclusions, providing a domain-independent foundation for analysing decentralization across heterogeneous systems.
Read the full abstract ▾
Systems and Control · Cross-listed from math.OC
Stochastic Multistage Constellation Reconfiguration Problem: Stochastic Dual Dynamic Integer Programming Approach
Brycen D. Pearl and Hang Woon Lee
Observation tasking is critical to satellite operations, enabling observation of planetary phenomena, orbital debris monitoring, and space domain awareness. To improve the effectiveness of satellite operations, orbital maneuverability is introduced as a leading-edge concept of operations within constellation reconfigurability for response to dynamic events. Previous investigations regarding constellation reconfigurability consist of deterministic mission environments, in which the formulations consider a priori knowledge of the environment; however, observation objectives inherently involve uncertainty at any given time. As such, scheduling satellite operations must account for uncertainties to ensure adequate observation tasking. In response, we present a
stochastic variant of the Multistage Constellation Reconfiguration Problem (MCRP) which is solved using
Stochastic Dual Dynamic Integer Programming (SDDiP). We additionally explore other
stochastic problem-solving techniques for solution quality comparison. To demonstrate each solution method, two computational experiments with
stochastic target properties are conducted. The first concerns random orbital targets, and the second concerns simulated hurricanes. The results of the experiments demonstrate the effectiveness of the SDDiP solution approach over other
stochastic problem-solving methods. Overall, the
stochastic MCRP accounts for target stochasticity while obeying visible time windows and maneuver feasibility.
Read the full abstract ▾