Systems and Control
Photovoltaic energy sharing: Implementation and tests on a real collective self-consumption system
Camblong H., Curea O., Ugartemendia J.J. et al. (+3 more)
This research study analyses different types of photovoltaic (PV) energy sharing in a collective self-consumption (CSC) real-case in the Izarbel technological park in France. The analysis is carried out above all from the point of view of the self-consumption rate (SCR) and the savings. After explaining the emergence of the self-consumption concept for the integration of renewable energies, the study case is described. The PV energy is produced in ESTIA1 building and consumed in ESTIA1, 2 and 4 buildings. The main IoT components used to implement the CSC are smart meters and the Tecsol TICs; devices based on the LoRa protocol to retrieve production and consumption data. Then, the characteristics of PV energy sharing in France are explained, in particular the three possible types of energy sharing/allocation (static, dynamic by default and customised dynamic) and the structure of the electricity bill. Finally, the three types of sharing are compared in four scenarios (without and with a data centre, for low and high
solar radiation). The results show that the dynamic allocations lead to increases of the SCR and that the customised dynamic sharing increases savings.
Read the full abstract ▾
All authors Camblong H., Curea O., Ugartemendia J.J., Boussaada Z., Lizarralde I., Etxegarai G
Systems and Control · Cross-listed from math.NA
Interpreting Moment Matrix Blocks Spectra using Mutual Shadow Area
Yaniv Brick, Francesco P. Andriulli and Mats Gustafsson
The mutual shadow area of pairs of surface regions is used for guiding the study of the spectral components and rank of their wave interaction, as captured by the corresponding moment
matrix blocks. It is demonstrated that the mutual shadow area provides an asymptotically accurate predictor of the location of the singular value curve knee. This predicted knee index is shown to partition the interacting parts of the range and domain of blocks into two subspaces that can be associated with different wave phenomena: an "aperture" subspace of dimension that scales with the subdomains area (or length in 2-D) and a remainder "diffraction" subspace of dimension that scales much slower with the electrical length, depending on the
geometric configuration. For interactions between open surface domains typical for the common hierarchical partitioning in most fast solvers, the latter can be attributed to the domain edges visible by its interacting counterpart. For interactions in 3-D with a small aspect angles between the source and observers, the diffraction subspace dimension is dominant in determining the rank until fairly large electrical lengths are reached. This explains the delayed asymptotic scaling of ranks and impressive fast solver performance observed in recent literature for seemingly arbitrary scatterers with no special
geometric characteristics. In the extreme cases of "endfire" reduced dimensionality interactions, where the shadow area vanishes, the diffraction governs also the asymptotic rank, which translates to superior asymptotic solver performance.
Read the full abstract ▾
Audio and Speech Processing · Cross-listed from cs.SD
dLLM-ASR: A Faster Diffusion LLM-based Framework for Speech Recognition
Wenjie Tian, Bingshen Mu, Guobin Ma et al. (+3 more)
Automatic
speech recognition (ASR) systems based on large
language models (LLMs) achieve superior performance by leveraging pretrained LLMs as decoders, but their
token-by-
token generation mechanism leads to inference latency that grows linearly with sequence length. Meanwhile, discrete
diffusion large
language models (dLLMs) offer a promising alternative, enabling high-quality parallel sequence generation with pretrained decoders. However, directly applying native text-oriented dLLMs to ASR leads to a fundamental mismatch between open-ended text generation and the acoustically conditioned transcription paradigm required by ASR. As a result, it introduces unnecessary difficulty and computational redundancy, such as denoising from pure noise, inflexible generation lengths, and fixed denoising steps. We propose dLLM-ASR, an efficient dLLM-based ASR framework that formulates dLLM's decoding as a prior-guided and adaptive denoising process. It leverages an ASR prior to initialize the denoising process and provide an anchor for sequence length. Building upon this prior, length-adaptive
pruning dynamically removes redundant
tokens, while confidence-based denoising allows converged
tokens to exit the denoising loop early, enabling
token-level adaptive computation. Experiments demonstrate that dLLM-ASR achieves recognition accuracy comparable to autoregressive LLM-based ASR systems and delivers a 4.44$\times$ inference speedup, establishing a practical and efficient paradigm for ASR.
Read the full abstract ▾
All authors Wenjie Tian, Bingshen Mu, Guobin Ma, Xuelong Geng, Zhixian Zhao, Lei Xie
Audio and Speech Processing
Speech Emotion Recognition with ASR Integration
Yuanchao Li
Speech Emotion Recognition (SER) plays a pivotal role in understanding human communication, enabling emotionally intelligent systems, and serving as a fundamental component in the development of Artificial General Intelligence (AGI). However, deploying SER in real-world, spontaneous, and low-resource scenarios remains a significant challenge due to the complexity of emotional expression and the limitations of current
speech and
language technologies. This thesis investigates the integration of Automatic
Speech Recognition (ASR) into SER, with the goal of enhancing the robustness, scalability, and practical applicability of
emotion recognition from spoken
language.
Read the full abstract ▾
Signal Processing
A Physics-Informed Digital Twin Framework for Calibrated Sim-to-Real FMCW Radar Occupancy Estimation
Huy Trinh, Sebastian Ratto V, Elliot Creager et al. (+1 more)
Learning robust radar perception models directly from real measurements is costly due to the need for controlled experiments, repeated calibration, and extensive annotation. This paper proposes a lightweight simulation-to-real (sim2real) framework that enables reliable Frequency Modulated Continuous Wave (FMCW) radar occupancy detection and people counting using only a physics-informed
geometric simulator and a small unlabeled real calibration set. We introduce calibrated domain randomization (CDR) to align the global noise-floor statistics of simulated range-Doppler (RD) maps with those observed in real environments while preserving discriminative micro-Doppler structure. Across real-world evaluations, ResNet18 models trained purely on CDR-adjusted simulation achieve 97 percent accuracy for occupancy detection and 72 percent accuracy for people counting, outperforming ray-tracing baseline simulation and conventional random domain randomization baselines.
Read the full abstract ▾
All authors Huy Trinh, Sebastian Ratto V, Elliot Creager, George Shaker
Systems and Control
Space-Air-Ground-Integrated Networks: The BER vs. Residual Delay and Doppler Analysis
Chao Zhang, Kunlun Li, Chao Xu et al. (+2 more)
Perfect Doppler compensation and synchronization is nontrivial due to multi-path Doppler effects and Einstein's theory of relativity in the space-air-ground-integrated networks (SAGINs). Hence, by considering the residual Doppler and the synchronization delay, this paper investigates the bit-error-rate (BER) performance attained under time-varying correlated Shadowed-Rician SAGIN channels. First, a practical SAGIN model is harnessed, encompassing correlated Shadowed-Rician channels, the Snell's law-based path loss, atmospheric absorption, the line-of-sight Doppler compensation, elliptical satellite orbits, and Einstein's theory of relativity. Then, a specific correlation coefficient between the pilot and data symbols is derived in the context of correlated Shadowed-Rician channels. By exploiting this correlation coefficient, the channel distribution is mimicked by a bi-variate Gamma distribution. Then, a closed-form BER formula is derived under employing least-square channel estimation and equalization for 16-QAM. Our analytical results indicate for a 300-km-altitude LEO that 1) the period of realistic elliptical orbits is around 0.8 seconds longer than that of the idealized circular orbits; and 2) the relativistic delay is lower than 1 microsecond over a full LEO pass (from rise to set). Our numerical results for the L bands quantify the effects of: 1) the residual Doppler; 2) atmospheric shadowing; 3) synchronization errors; and 4) pilot overhead.
Read the full abstract ▾
All authors Chao Zhang, Kunlun Li, Chao Xu, Lie-Liang Yang, Lajos Hanzo
Signal Processing · Cross-listed from cs.IT
Phase-Rotated Symbol Spreading for Scalable Rydberg Atomic-MIMO Detection
Jiuyu Liu, Yi Ma and Rahim Tafazolli
Multiple-input multiple-output (
MIMO) systems using Rydberg atomic (RA) receivers face significant scalability challenges in signal detection due to their nonlinear signal models. This letter proposes phase-rotated symbol spreading (PRSS), which transmits each symbol across two consecutive time slots with an optimal {\pi}/2 phase offset. PRSS enables reconstruction of an effective linear signal model while maintaining spectral efficiency and facilitating the use of conventional RF-
MIMO detection
algorithms. Simulation results demonstrate that PRSS achieves greater than 2.5 dB and 10 dB bit error rate improvements compared to current single-transmission methods when employing optimal exhaustive search and low-complexity sub-optimal detection methods, respectively.
Read the full abstract ▾
Signal Processing
Movable Antenna-Enhanced Near-Field Flexible Beamforming: Performance Analysis and Optimization
Shun Yang, Xin Wei, Nianbing Su et al. (+3 more)
As an emerging wireless communication technology, movable
antennas (MAs) offer the ability to adjust the spatial correlation of steering vectors, enabling more flexible beamforming compared to fixed-position
antennas (FPAs). In this paper, we investigate the use of MAs for two typical near-field beamforming scenarios: beam nulling and multi-beam forming. In the first scenario, we aim to jointly optimize the positions of multiple MAs and the beamforming vector to maximize the beam gain toward a desired direction while nulling interference toward multiple undesired directions. In the second scenario, the objective is to maximize the minimum beam gain among all the above directions. However, both problems are non-convex and challenging to solve optimally. To gain insights, we first analyze several special cases and show that, with proper positioning of the MAs, directing the beam toward a specific direction can lead to nulls or full gains in other directions in the two scenarios, respectively. For the general cases, we propose a discrete sampling method and an alternating optimization
algorithm to obtain high-quality suboptimal solutions to the two formulated problems. Furthermore, considering the practical limitations in
antenna positioning accuracy, we analyze the impact of position errors on the performance of the optimized beamforming and MA positions, by introducing a Taylor series approximation for the near-field beam gain at each target. Numerical results validate our theoretical findings and demonstrate the effectiveness of our proposed
algorithms.
Read the full abstract ▾
All authors Shun Yang, Xin Wei, Nianbing Su, Weidong Mei, Zhi Chen, Boyu Ning
Systems and Control · Cross-listed from cs.RO
Delay-Compensated Stiffness Estimation for Robot-Mediated Dyadic Interaction
Mingtian Du, Suhas Raghavendra Kulkarni, Bernardo Noronha et al. (+1 more)
Robot-mediated human-human (dyadic) interactions enable therapists to provide physical therapy remotely, yet an accurate perception of patient stiffness remains challenging due to network-induced haptic delays. Conventional stiffness estimation methods, which neglect delay, suffer from temporal misalignment between force and position signals, leading to significant estimation errors as delays increase. To address this, we propose a robust, delay-compensated stiffness estimation framework by deriving an algebraic
estimator based on quasi-static
equilibrium that explicitly accounts for temporally aligning the expert's input with the novice's response. A Normalised Weighted Least Squares (NWLS) implementation is then introduced to robustly filter dynamic bias resulting from the algebraic derivation. Experiments using commercial rehabilitation
robots (H-MAN) as the platform demonstrate that the proposed method significantly outperforms the standard
estimator, maintaining consistent tracking accuracy under multiple introduced delays. These findings offer a promising solution for achieving high-fidelity haptic perception in remote dyadic interaction, potentially facilitating reliable stiffness assessment in therapeutic settings across networks.
Read the full abstract ▾
All authors Mingtian Du, Suhas Raghavendra Kulkarni, Bernardo Noronha, Domenico Campolo
Signal Processing
Comparison of Single Carrier FTN-QAM and PCS-QAM for Amplifier-less Coherent Communication Systems
Dongdong Zou, Fan Li, Wei Wang et al. (+4 more)
A performance comparison of FTN-QAM and PCS-QAM for amplifier-less short-reach coherent communication systems is provided. With the applications of phase tracking partial response DFE and turbo equalization strategy, FTN-16QAM exhibits about 0.9dB power margin advantage over PCS-64QAM.
Read the full abstract ▾
All authors Dongdong Zou, Fan Li, Wei Wang, Zhongxing Tian, Yuheng Liu, Gangxiang Shen, Yi Cai
Signal Processing
Context-Aware Iterative Token Detection and Masked Transmission for Wireless Token Communication
Junyong Shin, Joohyuk Park, Jihong Park et al. (+2 more)
The success of large-scale
language models has established
tokens as compact and meaningful units for natural-
language representation, which motivates
token communication over wireless channels, where
tokens are considered fundamental units for wireless transmission. We propose a context-aware
token communication framework that uses a pretrained masked
language model (MLM) as a shared contextual probability model between the transmitter (Tx) and receiver (Rx). At Rx, we develop an iterative
token detection method that jointly exploits MLM-guided contextual priors and channel observations based on a
Bayesian perspective. At Tx, we additionally introduce a context-aware masking strategy which skips highly predictable
token transmission to reduce transmission rate. Simulation results demonstrate that the proposed framework substantially improves reconstructed sentence quality and supports effective rate adaptation under various channel conditions.
Read the full abstract ▾
All authors Junyong Shin, Joohyuk Park, Jihong Park, Jinho Choi, Yo-Seb Jeon
Image and Video Processing
A Capsule-Sized Multi-Wavelength Wireless Optical System for Edge-AI-Based Classification of Gastrointestinal Bleeding Flow Rate
Yunhao Bian, Dawei Wang, Mingyang Shen et al. (+5 more)
Post-endoscopic gastrointestinal (GI) rebleeding frequently occurs within the first 72 hours after therapeutic hemostasis and remains a major cause of early morbidity and mortality. Existing non-invasive monitoring approaches primarily provide binary blood detection and lack quantitative assessment of bleeding severity or flow dynamic, limiting their ability to support timely clinical decision-making during this high-risk period. In this work, we developed a capsule-sized, multi-wavelength optical sensing wireless platform for order-of-magnitude-level classification of GI bleeding flow rate, leveraging transmission spectroscopy and low-power edge artificial intelligence. The system performs time-resolved, multi-spectral measurements and employs a lightweight two-dimensional convolutional neural network for on-device flow-rate classification, with physics-based validation confirming consistency with wavelength-dependent hemoglobin absorption behavior. In controlled in vitro experiments under simulated gastric conditions, the proposed approach achieved an overall classification accuracy of 98.75% across multiple bleeding flow-rate levels while robustly distinguishing diverse non-blood gastrointestinal interference. By performing embedded inference directly on the capsule electronics, the system reduced overall energy consumption by approximately 88% compared with continuous wireless transmission of raw data, making prolonged, battery-powered operation feasible. Extending capsule-based diagnostics beyond binary blood detection toward continuous, site-specific assessment of bleeding severity, this platform has the potential to support earlier identification of clinically significant rebleeding and inform timely re-intervention during post-endoscopic surveillance.
Read the full abstract ▾
All authors Yunhao Bian, Dawei Wang, Mingyang Shen, Xinze Li, Jiayi Shi, Ziyao Zhou, Tiancheng Cao, Hen-Wei Huang
Signal Processing
Ampli-Flection for 6G: Active-RIS-Aided Aerial Backhaul with Full 3D Coverage
Hong-Bae Jeon and Chan-Byoung Chae
In this paper, we propose a novel aerial backhaul architecture that employs an aerial active reconfigurable intelligent surface (RIS) to achieve energy-efficient, {full 3D coverage including
UAV-BSs and ground users in 6G wireless networks}. Unlike prior aerial-RIS approaches limited to {2D coverage with only servicing ground users} or passive operation, the proposed design integrates an active-RIS onto a high-altitude aerial platform, enabling reliable line-of-sight links and overcoming multiplicative fading through amplification. In a scenario with
UAV-BSs deployed to handle sudden traffic surges in urban areas, the aerial-active-RIS both reflects and amplifies backhaul signals to overcome blockage. We jointly optimize the aerial platform placement, array partitioning, and RIS phase configuration to maximize
UAV-BS energy-efficiency. Simulation results confirm that the proposed method significantly outperforms
benchmarks, demonstrating its strong potential to deliver resilient backhaul connectivity with comprehensive 3D coverage in 6G networks.
Read the full abstract ▾
Signal Processing
Over-The-Air Extreme Learning Machines with XL Reception via Nonlinear Cascaded Metasurfaces
Kyriakos Stylianopoulos, Mattia Fabiani, Giulia Torcolacci et al. (+2 more)
The recently envisioned goal-oriented communications paradigm calls for the application of inference on wirelessly transferred data via Machine Learning (ML) tools. An emerging research direction deals with the realization of inference ML models directly in the physical layer of Multiple-Input Multiple-Output (
MIMO) systems, which, however, entails certain significant challenges. In this paper, leveraging the technology of programmable MetaSurfaces (MSs), we present an eXtremely Large (XL)
MIMO system that acts as an Extreme Learning Machine (ELM) performing binary classification tasks completely Over-The-Air (OTA), which can be trained in closed form. The proposed system comprises a receiver architecture consisting of densely parallel placed diffractive layers of XL MSs, also known as Stacked Intelligent Metasurfaces (SIM), followed by a single reception
radio-frequency chain. The front layer facing the XL
MIMO channel consists of identical unit
cells of a fixed NonLinear (NL) response, whereas the remaining layers of elements of tunable linear responses are utilized to approximate OTA the trained ELM weights. Our numerical investigations showcase that, in the XL regime of MS elements, the proposed XL-
MIMO-ELM system achieves performance comparable to that of digital and idealized ML models across diverse
datasets and wireless scenarios, thereby demonstrating the feasibility of
embedding OTA learning capabilities into future wireless systems.
Read the full abstract ▾
All authors Kyriakos Stylianopoulos, Mattia Fabiani, Giulia Torcolacci, Davide Dardari, George C. Alexandropoulos
Signal Processing
S-MDMA: Sensitivity-Aware Model Division Multiple Access for Satellite-Ground Semantic Communication
Hui Cao, Rui Meng, Shujun Han et al. (+3 more)
Satellite-ground semantic communication (SemCom) is expected to play a pivotal role in convergence of communication and AI (ComAI), particularly in enabling intelligent and efficient multi-user data transmission. However, the inherent bandwidth constraints and user interference in satellite-ground systems pose significant challenges to semantic fidelity and transmission robustness. To address these issues, we propose a sensitivity-aware model division multiple access (S-MDMA) framework tailored for bandwidth-limited multi-user scenarios. The proposed framework first performs semantic extraction and merging based on the MDMA architecture to consolidate redundant information. To further improve transmission efficiency, a semantic sensitivity sorting
algorithm is presented, which can selectively retain key semantic features. In addition, to mitigate inter-user interference, the framework incorporates orthogonal
embedding of semantic features and introduces a multi-user reconstruction loss function to guide joint optimization. Experimental results on open-source
datasets demonstrate that S-MDMA consistently outperforms existing methods, achieving robust and high-fidelity reconstruction across diverse signal-to-noise ratio (SNR) conditions and user configurations.
Read the full abstract ▾
All authors Hui Cao, Rui Meng, Shujun Han, Song Gao, Xiaodong Xu, Ping Zhang
Signal Processing
Doppler-Domain Respiratory Amplification for Semi-Static Human Occupancy Detection Using Low-Resolution SIMO FMCW Radar
Huy Trinh, Elliot Creager and George Shaker
Radar-based sensing is a promising
privacy-preserving alternative to cameras and wearables in settings such as long-term care. Yet detecting quasi-static presence (lying, sitting, or standing with only subtle micro-motions) is difficult for low-resolution SIMO FMCW radar because near-zero Doppler energy is often buried under static clutter. We present Respiratory-Amplification Semi-Static Occupancy (RASSO), an invertible Doppler-domain non-linear remapping that densifies the slow-time FFT (Doppler) grid around 0 m/s before adaptive Capon beamforming. The resulting range-azimuth (RA) maps exhibit higher effective SNR, sharper target peaks, and lower background variance, making thresholding and learning more reliable. On a real nursing-home
dataset collected with a short-range 1Tx-3Rx radar, RASSO-RA improves classical detection performance, achieving AUC = 0.981 and recall = 0.920/0.947 at FAR = 1%/5%, outperforming conventional Capon processing and a recent baseline. RASSO-RA also benefits data-driven models: a frame-based CNN reaches 95-99% accuracy and a sequence-based CNN-LSTM reaches 99.4-99.6% accuracy across subjects. A paired session-level bootstrap test confirms statistically significant macro-F1 gains of 2.6-3.6 points (95% confidence intervals above zero) over the non-warped pipeline. These results show that simple Doppler-domain warping before spatial processing can materially improve semi-static occupancy detection with low-resolution radar in real clinical environments.
Read the full abstract ▾
Audio and Speech Processing · Cross-listed from cs.SD
CaSNet: Compress-and-Send Network Based Multi-Device Speech Enhancement Model for Distributed Microphone Arrays
Chengqian Jiang, Jie Zhang and Haoyin Yan
Distributed microphone array (DMA) is a promising next-generation platform for
speech interaction, where
speech enhancement (SE) is still required to improve the
speech quality in noisy cases. Existing SE methods usually first gather raw waveforms at a fusion center (FC) from all devices and then design a multi-microphone model, causing high bandwidth and energy costs. In this work, we propose a Compress-and-Send Network (CaSNet) for resource-constrained DMAs, where one microphone serves as the FC and reference. Each of other devices encodes the measured raw data into a feature
matrix, which is then compressed by singular value decomposition (SVD) to produce a more compact representation. The received features at the FC are aligned via cross window query with respect to the reference, followed by neural decoding to yield spatially coherent enhanced
speech. Experiments on multiple
datasets show that the proposed CaSNet can save the data amount with a negligible impact on the performance compared to the uncompressed case. The reproducible code is available at https://github.com/Jokejiangv/CaSNet.
Read the full abstract ▾
Signal Processing
Reliable Quasi-Static Post-Fall Floor-Occupancy Detection Using Low-Cost Millimetre-Wave Radar
Huy Trinh, Phuong Thai, Elliot Creager et al. (+1 more)
As the population ages rapidly, long-term care (LTC) facilities across North America face growing pressure to monitor residents safely while keeping staff workload manageable. Falls are among the most critical events to monitor due to their timely response requirement, yet frequent false alarms or uncertain detections can overwhelm caregivers and contribute to alarm fatigue. This motivates the design of reliable, whole end-to-end ambient monitoring systems from occupancy and activity awareness to fall and post-fall detection. In this paper, we focus on robust post-fall floor-occupancy detection using an off-the-shelf 60 GHz FMCW radar and evaluate its deployment in a realistic, furnished indoor environment representative of LTC facilities. Post-fall detection is challenging since motion is minimal, and reflections from the floor and surrounding objects can dominate the radar signal return. We compare a vendor-provided digital beamforming (DBF) pipeline against a proposed preprocessing approach based on Capon or minimum variance distortionless response (MVDR) beamforming. A
cell-averaging constant false alarm rate (CA-CFAR) detector is applied and evaluated on the resulting range-azimuth maps across 7 participants. The proposed method improves the mean frame-positive rate from 0.823 (DBF) to 0.916 (Proposed).
Read the full abstract ▾
All authors Huy Trinh, Phuong Thai, Elliot Creager, George Shaker
Audio and Speech Processing · Cross-listed from cs.SD
Segment Length Matters: A Study of Segment Lengths on Audio Fingerprinting Performance
Ziling Gong, Yunyan Ouyang, Iram Kamdar et al. (+5 more)
Audio fingerprinting provides an identifiable representation of acoustic signals, which can be later used for identification and
retrieval systems. To obtain a discriminative representation, the input audio is usually segmented into shorter time intervals, allowing local acoustic features to be extracted and analyzed. Modern neural approaches typically operate on short, fixed-duration audio segments, yet the choice of segment duration is often made heuristically and rarely examined in depth. In this paper, we study how segment length affects audio fingerprinting performance. We extend an existing neural fingerprinting architecture to adopt various segment lengths and evaluate
retrieval accuracy across different segment lengths and query durations. Our results show that short segment lengths (0.5-second) generally achieve better performance. Moreover, we evaluate LLM capacity in recommending the best segment length, which shows that GPT-5-mini consistently gives the best suggestions across five considerations among three studied LLMs. Our findings provide practical guidance for selecting segment duration in large-scale neural audio
retrieval systems.
Read the full abstract ▾
All authors Ziling Gong, Yunyan Ouyang, Iram Kamdar, Melody Ma, Hongjie Chen, Franck Dernoncourt, Ryan A. Rossi, Nesreen K. Ahmed
Systems and Control
Composite Adaptive Control Barrier Functions for Safety-Critical Systems with Parametric Uncertainty
Mohammadreza Kamaldar
Control barrier functions guarantee safety but require accurate system models; parametric uncertainty invalidates these guarantees. Existing robust methods maintain safety via worst-case bounds at the cost of performance, while modular learning schemes decouple estimation from safety and risk constraint violations during transients. This paper presents the composite adaptive control barrier function (CaCBF)
algorithm for nonlinear control-affine systems with linear parametric uncertainty. The adaptation law is derived from a composite energy function integrating a logarithmic safety barrier, a control Lyapunov function, and a parameter-error term, creating a direct coupling between estimation accuracy and the safety margin. We prove three main results: (i) the safe set is forward invariant for all bounded parameters, without requiring persistence of excitation; (ii) the safety guarantee is robust to bounded errors in the state-derivative measurement; and (iii) all closed-loop signals are uniformly ultimately bounded. We further prove that the CaCBF admissible control set always contains the robust counterpart as a subset. Simulations of adaptive cruise control, an omnidirectional
robot, and a planar drone traversing a narrow gate confirm that CaCBF recovers the performance margin surrendered by robust methods while maintaining strict safety throughout.
Read the full abstract ▾
Audio and Speech Processing · Cross-listed from cs.SD
BanglaRobustNet: A Hybrid Denoising-Attention Architecture for Robust Bangla Speech Recognition
Md Sazzadul Islam Ridoy, Mubaswira Ibnat Zidney, Sumi Akter et al. (+1 more)
Bangla, one of the most widely spoken
languages, remains underrepresented in state-of-the-art automatic
speech recognition (ASR) research, particularly under noisy and speaker-diverse conditions. This paper presents BanglaRobustNet, a hybrid denoising-
attention framework built on Wav2Vec-BERT, designed to address these challenges. The architecture integrates a
diffusion-based denoising module to suppress environmental noise while preserving Bangla-specific phonetic cues, and a contextual cross-
attention module that conditions recognition on speaker
embeddings for robustness across gender, age, and dialects. Trained end-to-end with a composite objective combining CTC loss, phonetic consistency, and speaker
alignment, BanglaRobustNet achieves substantial reductions in word error rate (WER) and character error rate (CER) compared to Wav2Vec-BERT and Whisper baselines. Evaluations on Mozilla Common Voice Bangla and augmented noisy
speech confirm the effectiveness of our approach, establishing BanglaRobustNet as a robust ASR system tailored to low-resource, noise-prone linguistic settings.
Read the full abstract ▾
All authors Md Sazzadul Islam Ridoy, Mubaswira Ibnat Zidney, Sumi Akter, Md. Aminur Rahman
Systems and Control
Battery-less Long-Range LTE-M Water Leak Detector
Roshan Nepal, Brandon Brown, Shishangbo Yu et al. (+3 more)
This work presents a self powered water leak sensor that eliminates both batteries and local gateways. The design integrates a dual compartment electrochemical harvester, a low input boost converter with supercapacitor storage, and a comparator gated LTE-M
radio built on the Nordic Thingy:91 platform. Laboratory tests confirm that the system can be awakened from a dormant state in the presence of water, harvest sufficient energy, and issue repeated cloud beacons using the water exposure as the power source. Beyond conventional LTE-M deployments, the system's compatibility with 3GPP standard cellular protocols paves the way for future connectivity via non terrestrial 5G networks, enabling coverage in infrastructure scarce regions.
Read the full abstract ▾
All authors Roshan Nepal, Brandon Brown, Shishangbo Yu, Roozbeh Abbasi, Norman Zhou, George Shaker
Systems and Control
Battery-Free and Gateway-Free Cellular IoT Water Leak Detection System
Roshan Nepal, Brandon Brown, Shishangbo Yu et al. (+3 more)
This paper presents a battery-free and gateway-free water leak detection system capable of direct communication over LTE-M (Cat-M1). The system operates solely on energy harvested through a hydroelectric mechanism driven by an electrochemical sensor, thereby removing the need for conventional batteries. To address the stringent startup and operational power demands of LTE-M transceivers, the architecture incorporates a compartmentalized sensing module and a dedicated power management subsystem, comprising a boost converter, supercapacitor based energy storage, and a hysteresis controlled load isolation
circuit. This design enables autonomous, direct to cloud data transmission without reliance on local networking infrastructure. Experimental results demonstrate consistent LTE-M beacon transmissions triggered by water induced energy generation, underscoring the system's potential for sustainable, maintenance free, and globally scalable IoT leak detection applications in smart infrastructure.
Read the full abstract ▾
All authors Roshan Nepal, Brandon Brown, Shishangbo Yu, Roozbeh Abbasi, Norman Zhou, George Shaker
Audio and Speech Processing · Cross-listed from cs.SD
AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
Xilin Jiang, Qiaolin Wang, Junkai Wu et al. (+30 more)
Internet audio-visual clips convey meaning through time-varying sound and motion, which extend beyond what text alone can represent. To examine whether AI models can understand such signals in human cultural contexts, we introduce AVMeme Exam, a human-curated
benchmark of over one thousand iconic Internet sounds and
videos spanning
speech, songs, music, and sound effects. Each meme is paired with a unique Q&A assessing levels of understanding from surface content to context and
emotion to usage and world knowledge, along with metadata such as original year, transcript, summary, and sensitivity. We systematically evaluate state-of-the-art
multimodal large
language models (MLLMs) alongside human participants using this
benchmark. Our results reveal a consistent limitation: current models perform poorly on textless music and sound effects, and struggle to think in context and in culture compared to surface content. These findings highlight a key gap in human-aligned
multimodal intelligence and call for models that can perceive contextually and culturally beyond the surface of what they hear and see. Project page: avmemeexam.github.io/public
Read the full abstract ▾
All authors Xilin Jiang, Qiaolin Wang, Junkai Wu, Xiaomin He, Zhongweiyang Xu, Yinghao Ma, Minshuo Piao, Kaiyi Yang, Xiuwen Zheng, Riki Shimizu, Yicong Chen, Arsalan Firoozi, Gavin Mischler, Sukru Samet Dindar, Richard Antonello, Linyang He, Tsun-An Hsieh, Xulin Fan, Yulun Wu, Yuesheng Ma, Chaitanya Amballa, Weixiong Chen, Jiarui Hai, Ruisi Li, Vishal Choudhari, Cong Han, Yinghao Aaron Li, Adeen Flinker, Mounya Elhilali, Emmanouil Benetos, Mark Hasegawa-Johnson, Romit Roy Choudhury, Nima Mesgarani
Signal Processing · Cross-listed from cs.LG
RPNT: Robust Pre-trained Neural Transformer – A Pathway for Generalized Motor Decoding
Hao Fang, Ryan A. Canfield, Tomohiro Ouchi et al. (+3 more)
Brain motor decoding aims to interpret and translate neural activity into behaviors. Decoding models should generalize across variations, such as recordings from different
brain sites, experimental sessions, behavior types, and subjects, will be critical for real-world applications. Current decoding models only partially address these challenges. In this work, we develop a pretrained neural
transformer model, RPNT - Robust Pretrained Neural
Transformer, designed to achieve robust generalization through pretraining, which in turn enables effective finetuning for downstream motor decoding tasks. We achieved the proposed RPNT architecture by systematically investigating which
transformer building blocks could be suitable for neural spike activity modeling, since components from models developed for other modalities, such as text and images, do not transfer directly to neural data. The final RPNT architecture incorporates three unique enabling components: 1) Multidimensional rotary positional
embedding to aggregate experimental metadata such as site coordinates, session ids and behavior types; 2) Context-based
attention mechanism via convolution kernels operating on global
attention to learn local temporal structures for handling non-stationarity of neural population activity; 3) Robust self-supervised learning objective with
stochastic causal masking strategies and contrastive representations. We pretrained two versions of RPNT on distinct
datasets that present significant generalization challenges: a) Multi-session, multi-task, and multi-subject microelectrode
benchmark; b) Multi-site recordings using high-density Neuropixel 1.0 probes from many cortical locations. After pretraining, we evaluated RPNT generalization on cross-session, cross-type, cross-subject, and cross-site downstream behavior decoding tasks. Our RPNT consistently outperforms the existing decoding models on these tasks.
Read the full abstract ▾
All authors Hao Fang, Ryan A. Canfield, Tomohiro Ouchi, Beatrice Macagno, Eli Shlizerman, Amy L. Orsborn
Audio and Speech Processing
End-to-End Joint ASR and Speaker Role Diarization with Child-Adult Interactions
Anfeng Xu, Tiantian Feng, Somer Bishop et al. (+2 more)
Accurate transcription and speaker role diarization of child-adult spoken interactions are crucial for developmental and clinical research. However, manual annotation is time-consuming and challenging to scale. Existing automated systems typically rely on cascaded speaker diarization and automatic
speech recognition pipelines, which can lead to error propagation. This paper presents a unified end-to-end framework that extends the Whisper encoder-decoder architecture to jointly model ASR and child-adult speaker role diarization. The proposed approach integrates: (i) a serialized output training scheme that emits speaker tags and start/end timestamps, (ii) a lightweight frame-level diarization head that enhances speaker-discriminative encoder representations, (iii) diarization-guided silence suppression for improved temporal precision, and (iv) a state-machine-based forced decoding procedure that guarantees structurally valid outputs. Comprehensive evaluations on two
datasets demonstrate consistent and substantial improvements over two cascaded baselines, achieving lower multi-talker word error rates and demonstrating competitive diarization accuracy across both Whisper-small and Whisper-large models. These findings highlight the effectiveness and practical utility of the proposed joint modeling framework for generating reliable, speaker-attributed transcripts of child-adult interactions at scale. The code and model weights are publicly available
Read the full abstract ▾
All authors Anfeng Xu, Tiantian Feng, Somer Bishop, Catherine Lord, Shrikanth Narayanan