Audio and Speech Processing
SE-AGCNet: An End-to-End Framework for Joint Speech Enhancement and Loudness Control in Meeting Scenarios
Jinming Zhang, Wei Rao, Xionghu Zhong et al. (+1 more)
Conventional audio pipelines typically treat
speech enhancement (SE) and automatic gain control (AGC) as discrete modules, which often limits overall performance. For instance, applying AGC before SE may inadvertently amplify background noise, while prioritizing SE tends to over-suppress low-volume
speech. To address these limitations, we propose SE-AGCNet, an end-to-end framework that jointly optimizes SE and AGC. Tailored for meeting scenarios with significant volume variations, SE-AGCNet leverages the synergy between the two tasks: SE preserves quiet
speech, thereby facilitating effective volume adjustment by the AGC component. Furthermore, we propose a specialized data simulation pipeline, SE-AGC-DataGen, and incorporate standardized loudness evaluation metrics: integrated loudness (LUFS), short-term loudness (St LUFS), and LRA. Experiments show that SE-AGCNet consistently achieves target loudness while improving
speech quality and ASR accuracy over competitive baselines.
Read the full abstract ▾
All authors Jinming Zhang, Wei Rao, Xionghu Zhong, Eng Siong Chng
Image and Video Processing · Cross-listed from cs.CV
Pulmonary Embolism Risk Stratification from CTPA and Medical Records: Vascular Graphs Are Not All You Need
Nathan Painchaud, Tristan Habémont, Morgane des Ligneris et al. (+6 more)
Risk stratification for pulmonary embolism (PE) is critical for clinical decision-making. Stratification guidelines are based on patient medical records, parameters measured from computed
tomography pulmonary angiography (CTPA), and blood tests. However, blood tests are often missing in routine practice. This work studies whether state-of-the-art models can accurately classify risk stratification from only medical records and biomarkers extracted from CTPA images. We
benchmark different approaches to combine medical records and cardiac biomarkers with rich pulmonary vascular information; we add vascular biomarkers to tabular models and apply graph neural networks (GNNs) on the vascular tree's intrinsic graph representation. We use a private
dataset (n=353) with uniquely complete data for PE risk stratification. Our results show that, among global features, medical records and cardiac biomarkers are the most significant predictors, while vascular biomarkers do not further improve stratification. Even more surprising, even GNNs on vascular graphs fail to outperform strong tabular baseline on global features. We consider hypotheses, on both models and data, that could explain this suboptimal performance. Our investigation suggests that, counter-intuitively, vascular graphs might hold no discriminative information for PE risk stratification. Code is available from https://github.com/creatis-myriad/GENESIS.
Read the full abstract ▾
All authors Nathan Painchaud, Tristan Habémont, Morgane des Ligneris, Allan Serva, Pierre Croisille, Laurent Bertoletti, Thomas Lampert, Johannes F. Lutzeyer, Odyssée Merveille
Systems and Control · Cross-listed from cs.HC
Explainable Control Framework (XCF) based on Fuzzy Model-Agnostic Explanation and LLM Agent-Supported Interface
Faliang Yin, Hak-Keung Lam and David Watson
Increasing demand for precise and reliable control in complex scenarios has led to the development of increasingly sophisticated controllers, including data-driven approaches employing closed box models and mathematically rigorous yet complex designs. This complexity highlights the needs for explainable control that can provide human-understandable insights into controller behavior. In this paper, an explainable control framework (XCF) along with supporting
algorithms and user interface are proposed to explain how controllers determine their control actions and their underlying working mechanism. The novel contributions of this work are threefold: First, the XCF is designed to provide model-agnostic explanations for controllers in closed-loop systems and can optionally refine local explanations by system response dynamics. Second, a novel explanation method, hierarchical fuzzy model-agnostic explanation for control systems (HFMAE-C), is proposed based on the designed framework. The HFMAE-C employs a fuzzy logic system to approximate the controller's behavior and system dynamics, providing sample, local, domain and universe level explanations via IF-THEN rules revealing the controller's decision logic and salience values quantifying the contribution of system states to control actions. Third, a large
language model
agent-supported user interface is developed to automatically analyze user requirements, select appropriate
algorithms, interpret the generated explanations to a natural
language report, and provide interactive consultation. Case studies on inverted pendulum system and Turtlebot obstacle avoidance demonstrate the effectiveness of the proposed method through simulated user experiments and quantitative comparisons with mainstream explainable control approaches.
Read the full abstract ▾
Image and Video Processing
Improving Richardson–Lucy Deconvolution with Diffusion Priors for Fluorescence Microscopy
Hao Chen and Scott S. Howard
Richardson–Lucy (RL) deconvolution improves fluorescence microscopy images by recovering details lost to diffraction. It estimates the fluorescence signal most likely to have produced the measured
photon counts under a Poisson imaging model. However, deconvolution remains ill-posed, especially at low
photon counts, when weak biological structures become difficult to distinguish from shot noise and the prior strongly influences the reconstruction. RL recovers structure in early iterations but can amplify noise and become unstable, while regularizers such as total variation (TV) reduce these artifacts at the cost of oversmoothing. Instead, we learn a prior from real fluorescence microscopy images and use its gradient within an inverse-problem framework. The prior is estimated using an unconditional score-based
diffusion model trained on a large microscopy
dataset. At each step, the learned prior guides RL toward plausible specimen structures, while RL enforces Poisson consistency with the measured counts. Across diverse biological samples and cellular morphologies, the framework reduces RL noise amplification while better preserving weak structures at low
photon counts.
Read the full abstract ▾
Systems and Control
Robustness and Centrality in Markov-switching Networks
Sarah H. Cen, Vaibhav Srivastava and Naomi Ehrich Leonard
We investigate how time-varying interactions, modeled via a Markov switching graph (MSG), impact the robustness of noisy multi-
agent dynamics in both continuous- and discrete-time settings. Our focus is on the steady-state performance of consensus and leader-follower tracking dynamics subject to
stochastic noise. Using the framework of Markov jump linear systems (MJLS), we derive expressions for the steady-state covariance of each
agent's deviation from consensus and tracking error, respectively, and use them to quantify individual and group performance as a function of the interaction graphs and the switching dynamics. We extend established notions of robustness, certainty indices, and joint centrality from static graphs to the MSG setting. To gain analytical insight, we specialize our results to systems switching between two
topologies and characterize how switching influences performance. Numerical simulations further illustrate how switching
topologies affects system robustness in both coordination tasks.
Read the full abstract ▾
Signal Processing
Sequential and Generative Models for Vehicular Distributed MIMO Channel Prediction
Malek Abida, Rafik Zayani, Eric Simon et al. (+1 more)
Vehicular communication is a key 6G use case requiring reliable and high-capacity connectivity under fast mobility and highly time-varying propagation conditions. However, large-scale vehicular channel estimation is costly and limited, impacting system-level performance of vehicular communications, and realistic channel prediction models are needed. This paper proposes a vehicular channel prediction framework based on real measured urban channels collected through a dedicated measurement campaign using the MaMIMOSA channel sounder. The framework enables the training and systematic benchmarking of sequential and generative models for both single-step and multi-horizon vehicular channel state information (CSI) prediction to assess prediction robustness across different
forecasting horizons, including LSTM, TCN, a CNN-enhanced
Transformer, and ChannelGPT, with the goal of accurately predicting channel
evolution while preserving spatiotemporal dynamics and non-stationarity. In addition, a system-level evaluation framework is introduced to assess the impact of channel prediction on the performance of vehicular distributed
MIMO communications. Using predicted channels, spectral efficiency (SE) is evaluated against true CSI. Results show that ChannelGPT achieves over 94% normalized mean squared error (NMSE) reduction compared to LSTM and significant improvements over other baselines, while reducing FLOPs by 28% and inference latency by 39% relative to the CNN +
Transformer. Moreover, ChannelGPT-predicted channels yield SE distributions nearly indistinguishable from those obtained with real measurements, demonstrating its effectiveness for reliable performance evaluation in high-mobility 6G vehicular networks.
Read the full abstract ▾
All authors Malek Abida, Rafik Zayani, Eric Simon, Davy Gaillot
Signal Processing
Networked Control System Under Controller-Actuator Channel Jamming
Chen Quan, Geethu Joseph and Gourab Ghatak
Wireless channels in the networked control systems are vulnerable to intentional interference, such as jamming attacks. This paper investigates jamming attacks on the wireless controller actuator channel of a control system that can tolerate occasional control inputs from the controller. We start with a worst case scenario for the jammer where the controller knows its channel state. We develop an adaptive jamming strategy in which the jammer, observing the success or failure of each controller transmission, forms beliefs about its own and the controller actuator channel states. Using this belief, it optimizes its actions under a limited jamming budget. To counter this, we develop an event-triggered defense scheme for the controller in two settings: with and without the knowledge of its channel state. Simulation results show that optimal adaptive jamming attacks can significantly degrade control performance, even with a limited budget, while the defense scheme, even without channel state knowledge, can effectively reduce this impact.
Read the full abstract ▾
Signal Processing
Deep Learning-Assisted Multicast Subgrouping in Massive MIMO
Alejandro de la Fuente, Leopoldo Carro-Calvo and Giovanni Interdonato
Efficient content delivery in massive multiple-input multiple-output (mMIMO) multicasting is fundamentally limited by pilot overhead and the need to serve heterogeneous users with a common transmission rate. Conventional approaches either suffer from pilot contamination or are constrained by the worst-user effect, motivating the need for adaptive subgrouping strategies. In this paper, we propose a deep learning-assisted multicast subgrouping framework that infers the number of multicast subgroups directly from users' spatial channel statistics. A snapshot-specific principal component analysis (PCA) is applied to user covariance
matrices to obtain a compact representation, which is processed by a sequential long short-term
memory (LSTM) encoder capable of handling variable-size user sets. The model predicts the number of subgroups and groups of users based on their statistical similarity. To further improve system performance, we introduce a transfer learning (TL) extension where a pretrained LSTM encoder is reused, and a lightweight dense head is fine-tuned to estimate the sum spectral efficiency (SE) as a function of the subgroup configuration. This enables selecting near-optimal subgrouping solutions without exhaustive search. Simulation results demonstrate that the proposed approach consistently outperforms
benchmark methods, including unicast transmission, conventional multicast, random subgrouping, and density-based clustering. The TL-enhanced model achieves up to 85% of the maximum achievable spectral efficiency while maintaining robust performance across diverse spatial user distributions and under imperfect covariance information.
Read the full abstract ▾
Signal Processing
CSI-CLIP++: A Scalable Channel Foundation Model for Wireless Communication via CIR-CSI Consistency
Jun Jiang, Wenjun Yu, Yunfan Li et al. (+2 more)
Self-supervised learning can exploit large-scale unlabeled channel data to improve the transferability of wireless AI models. Existing channel foundation models are often built on single-domain representations or reconstruction-oriented objectives, which may not explicitly capture the physical correspondence between frequency- and delay-domain channel views. This paper proposes CSI-CLIP++, a scalable channel foundation model for
MIMO wireless channels. CSI-CLIP++ treats frequency-domain channel state information (CSI) and delay-domain channel impulse response (CIR) as paired views of the same propagation process and learns transferable representations through CSI-CIR contrastive
alignment. The pretrained CSI encoder is adapted to channel identification, beam prediction, and positioning, representing PHY, RAN, and
ISAC applications. Experiments on large-scale DeepMIMO scenarios show consistent gains over supervised baselines across environments, carrier frequencies, and data scales. CSI-CLIP++ improves beam prediction Top-1 accuracy by up to 19.31 percentage points and achieves competitive positioning performance, including cross-simulator transfer on a Sionna RT
dataset. Backbone scaling results further show that the proposed objective remains effective across encoder architectures and benefits from larger model capacity.
Read the full abstract ▾
All authors Jun Jiang, Wenjun Yu, Yunfan Li, Yuan Gao, Shugong Xu
Signal Processing
Empirical characterization of the Translational acoustic-RF communication channel
Ann Pamela Mathew, V. V. Reddy and S. L. Srinivas
Translational acoustic-
radio frequency (TARF) communication paves the way for translating information from an
underwater acoustic signal to the over-the-air (OTA) electromagnetic receiver through the medium interface. The study and characterization of the channel is essential for establishing a reliable communication link. Although channel modeling has been extensively studied for OTA and
underwater channels, the amplitude characteristics of the TARF cross-medium channel have not been investigated in comparison with well-known distributions to date. In this work, we define the signal model incorporating the effects of the wavefront-water surface interactions. With the help of numerical and graphical methods, we then attempt to characterize the cross-medium channel with empirical data using existing models developed for OTA and
underwater channels. We further evaluate channel linearity and time invariance empirically. Observations from these studies over multiple experiments are detailed with additional discussions that enable better channel characterization to develop reliable and consistent cross-medium TARF communication in challenging scenarios.
Read the full abstract ▾
Systems and Control · Cross-listed from cs.RO
Average-Power-Budgeted Underwater Vehicle Control via Constrained Reinforcement Learning
Yinuo Wang, Gavin Tao, Yuze Liu et al. (+1 more)
Underwater vehicles operate from a fixed onboard energy budget that propulsion rapidly depletes, so a controller that completes its task while drawing less thruster power directly extends mission range and endurance. Reinforcement learning yields capable model-free controllers for station-keeping and trajectory tracking, but optimizing task accuracy alone drives the policy toward oscillatory, energy-wasting actuation. The established remedy subtracts an energy penalty from the reward, yet this sets the task-power trade-off through a single weight with no physical units: a target power level cannot be specified, the weight must be re-tuned for every vehicle and task, and a mismatched weight can even raise power. This paper instead formulates energy-efficient
underwater control as a constrained Markov decision process in which average thruster power is subject to an explicit budget, solved with a PPO-Lagrangian
algorithm. The power level is set by declaring a budget in physical units, and a single dual variable is updated online to meet it for each vehicle and task, without manual weight search. Across three vehicles and four tasks in the MarineGym simulator, the energy-constrained policy draws the least power in all twelve settings, reducing it by 14–65% (up to 64.9%) over a task-only baseline and below an energy-reward baseline everywhere, while remaining the smoothest in ten settings and preserving task accuracy except in one deliberately power-limited regime. Imposing energy as an explicit constraint thus offers a tuning-free route to energy-efficient
underwater control that needs no per-vehicle, per-task weight search.
Read the full abstract ▾
All authors Yinuo Wang, Gavin Tao, Yuze Liu, John V. Ringwood
Audio and Speech Processing
Joint Residual Reweighting for Classifier Free Guidance in Flow-Matching Zero-Shot TTS
Runwu Shi, Yujin Wang, Hongjin Song et al. (+8 more)
Classifier-free guidance (CFG) is widely used in flow-matching-based zero-shot text-to-
speech (TTS), where generation is conditioned on text content and a
speech prompt. Standard CFG uses a single guidance weight for their joint conditional effect, while branch-selective guidance emphasizes text or speaker conditioning and can introduce a trade-off between text accuracy and speaker similarity. In this paper, we revisit CFG under independently masked conditions and decompose the guidance field into text, speaker, and joint residuals. We show that condition-specific branch differences couple the joint residual with the corresponding text or speaker residual under a shared weight. Trajectory analysis further shows that the joint residual varies over flow time and contains information that cannot be represented by reweighting the text and speaker residuals alone. Based on these observations, we propose joint residual reweighting, which assigns independent weights to the three residuals. Experiments on F5-TTS, CosyVoice2, and GLM-TTS across three evaluation sets show overall improvements in speaker similarity and text accuracy over the default CFG settings without retraining.
Read the full abstract ▾
All authors Runwu Shi, Yujin Wang, Hongjin Song, Jiang Wang, Yaozhong Kang, Nabeela Khan, Weiqiao Shan, Benjamin Yen, Ashizawa Takeshi, Chunxiang Jin, Kazuhiro Nakadai
Signal Processing
Optimization-Based Velocity-Integral Sliding-Window Coarse Alignment: Attitude Error Analysis and Validation
Xuyang Jiang, Xiyuan Chen and Weiming Jing
The optimization-based
alignment (OBA) approach transforms strapdown inertial
navigation system (SINS) coarse
alignment into a constant initial attitude estimation problem for global
navigation satellite system (GNSS)-aided in-motion
alignment. While existing studies mainly improve accuracy by refining attitude determination
algorithms or constructing robust observation vectors, a rigorous analytical mapping from raw sensor and aiding-velocity uncertainties to attitude errors remains unavailable for fixed-length sliding-window velocity-integral OBA. To address this issue, this paper proposes a first-order attitude error propagation model. Based on the sliding-window observation model, gyroscope errors, accelerometer errors, GNSS velocity noise, and lever-arm effects are propagated to unnormalized observation-vector perturbations, which are further mapped to attitude misalignment through Davenport's q method. The model decouples systematic errors from
stochastic noise and derives the corresponding deterministic attitude offsets and error covariances. Monte Carlo simulations demonstrate that the analytical model captures deterministic offsets and statistical spread, yielding standard-deviation ratios between 0.942 and 1.036 with empirical coverage above 99.4%. Vehicle field tests show that the predicted covariance envelopes bound the actual initial-attitude errors, with the maximum residual root-mean-square error (RMSE) below 0.00495 deg. These results validate the proposed model for coarse-
alignment attitude error assessment.
Read the full abstract ▾
Signal Processing · Cross-listed from cs.RO
Event-Adaptive Motion Planning with Distilled Vision-Language Model in Safety-Critical Situations
Zhenwei Huang, Changsheng You, Shuai Wang et al. (+3 more)
Robot navigation in safety-critical scenarios faces significant challenges from unforeseen semantic events, where collisions arise primarily from the unpredictable behaviors of dynamic
agents rather than unseen objects. While large
vision-
language models (VLMs) offer remarkable capabilities in commonsense
reasoning, frequently invoking them within the continuous control loop introduces severe computational latency, fundamentally destabilizing physical execution. To address these challenges, we propose event-adaptive motion planning (EAMP), an efficient framework for VLM-based
robot navigation. Specifically, a
prompt-configurable semantic event trigger (PC-SET) selectively activates semantic intervention by continuously monitoring short temporal clips for behavioral anomalies. Upon triggering, an event-triggered distilled SemNav-VLM, fine-tuned via physically verified semantic
distillation, maps detected anomalies into discrete strategy-level decisions. Subsequently, a semantic model predictive control (SMPC) module translates these strategies into dynamic reconfigurations of optimization objectives and
geometric references. Extensive experiments in safety-critical logistics scenarios demonstrate that EAMP effectively aligns high-level
reasoning with low-level control, significantly improving dynamic safety margins over existing baselines while preserving real-time efficiency.
Read the full abstract ▾
All authors Zhenwei Huang, Changsheng You, Shuai Wang, Chao Zhou, Wei Xu, Yi Gong
Image and Video Processing · Cross-listed from cs.RO
1000 Rallies: An Event-Camera Dataset and Real-Time Learned Ball-State Estimation for Robotic Table Tennis
Raphaela Kreiser, Asude Aydin, Yin Bi et al. (+3 more)
Robotic table tennis has emerged as a compelling
benchmark for real-time robotic perception due to its fast ball dynamics and stringent timing requirements. Accurate, high-frequency, and low-latency ball state estimation is critical for reliable trajectory prediction and timely control. Traditional frame-based cameras face an inherent trade-off: low frame rates leave temporal blind spots that miss fast-moving objects and high frame rates raise data and computational cost. Event cameras instead offer microsecond temporal resolution and, under sufficient illumination, remain largely free of motion blur even at high ball speeds. However, the community lacks large-scale
datasets to develop and
benchmark event-based perception in realistic sports scenarios. We address this gap by introducing the first large-scale event-camera
dataset for table tennis, comprising over 1000 rallies from a diverse group of players ranging from amateurs to elite-level athletes. Each recording captures the event stream alongside 14 synchronized high-speed frame-based cameras at 200 FPS, which we use to produce 1 kHz pseudo ground-truth labels for ball position, velocity, and
spin. Building on this
dataset, we train a convolutional neural network robust to background player motion that jointly estimates the ball's position and velocity in the image-plane from events. Treating the predicted velocity as an additional measurement in the Kalman filter reduces bounce-point prediction error by 36% relative to a position-only baseline. Finally, we close the perception-action loop by integrating the event-based system with a Stäubli robotic arm, enabling the first real-time human-
robot table tennis rallies driven by event-based perception.
Read the full abstract ▾
All authors Raphaela Kreiser, Asude Aydin, Yin Bi, Claudio Fanconi, Peter Dürr, Naoya Takahashi
Systems and Control
Reference-Free Heterogeneous Multi-Agent Reinforcement Learning for Grid-Friendly Tie-Line Power Shaping in Industrial Microgrids
Daniyaer Paizulamua, Lin Cheng, Fashun Shi et al. (+3 more)
Tie-line power (TLP) shaping is a key requirement for the grid-friendly operation of industrial microgrids (IMGs). This paper studies the coordination of multi-timescale heterogeneous adjustable resources in a steel IMG to shape a grid-friendly TLP trajectory considering multiple objectives. A sequential heterogeneous-
agent coordination (SHAC) framework is proposed, where process loads, hydrogen storage, and battery storage are modeled as functionally heterogeneous
agents with cross-role observations, asynchronous decision intervals, role-specific rewards and critics. This design captures the heterogeneous temporal effects of different resources on the TLP trajectory and alleviates ambiguous credit assignment and weak inter-
agent coordination. To ensure feasible real-time execution, process-knowledge-based action masking and feasibility projection are embedded into policy execution, and a role-aware multi-timescale actor–critic training scheme is developed for
agents with different action structures and decision intervals. Numerical studies using real renewable generation and electricity
market data show that SHAC effectively eliminates the dependence on predefined reference trajectories and enables adaptive 1-min online decision-making, achieving zero production failures with an average computational time of only 0.4 ms per step. Compared with the original operation, SHAC reduces the total grid purchase cost, contract-demand exceedance time, and cumulative ramp excess by 91.27%, 98.64%, and 96.91%, respectively. These results demonstrate that the proposed framework improves the economic efficiency and grid friendliness of industrial microgrid operation while satisfying strict process-safety constraints and real-time computational requirements.
Read the full abstract ▾
All authors Daniyaer Paizulamua, Lin Cheng, Fashun Shi, Haoyu Zheng, Pengfei He, Haiwang Zhong
Image and Video Processing
Cross-Attention Multimodal Learning for Predicting Response to Neoadjuvant Imatinib in Gastrointestinal Stromal Tumors: A Multicenter Retrospective Study
Fariba Tohidinezhad, Douwe J. Spaanderman, Natalia Oviedo Acosta et al. (+14 more)
Background: Response to neoadjuvant imatinib in gastrointestinal stromal tumors (GISTs) is highly variable and cannot be reliably predicted using current clinical or molecular markers. This study developed and evaluated an explainable
multimodal deep learning framework integrating computed
tomography (CT) imaging and clinical variables to predict treatment response. Methods: Patients from four tertiary centers were retrospectively included between 2000-2023 in independent pretraining (n=935) and prediction (n=213) cohorts. A cross-
attention framework integrating clinical variables and tumor-centered CT imaging was developed to predict response to neoadjuvant imatinib. Two training strategies were evaluated: (1) self-supervised pretraining with low-rank adaptation and (2) training from scratch. Hyperparameters were optimized using SMAC3. Performance was assessed through internal cross-validation and external testing. Ablation analyses and
attention-based explanations were used to quantify modality contributions. Results: Among 213 patients (54.5% responders), responders had larger tumors (112 vs. 89 mm, P=0.026), higher mitotic index (3 vs. 0, P<0.001), and more frequent KIT mutations (69.0% vs. 56.7%, P=0.019). Cross-
attention models achieved the highest internal performance (AUC up to 0.99) but lower external performance (AUC 0.60-0.63). Clinical-only performance was moderate (AUC 0.66), whereas imaging-only models showed limited generalizability (AUC 0.56-0.66). Explainability analyses identified significant differences in feature importance between responders and non-responders, including CD117, BRAF, PDGFRA, age, sex, disease status, and comorbidities (FDR-adjusted P<=0.036). Conclusion: The cross-
attention framework shows potential for improving imatinib response prediction in GIST while providing interpretable insights into
multimodal determinants of treatment response.
Read the full abstract ▾
All authors Fariba Tohidinezhad, Douwe J. Spaanderman, Natalia Oviedo Acosta, Kaouther Mouheb, Karthik Prathaban, David F. Hanff, Dirk J. Grünhagen, Cornelis Verhoef, Joris M. van Sabben, Evelyne Roets, Jette J. Slettenhaar, Hans Gelderblom, Ingrid M.E. Desar, Anna K.L. Reyners, Neeltje Steeghs, Stefan Klein, Martijn P.A. Starmans
Signal Processing
MCRB and MSE Analysis for Parameter Estimation in AFDM-ISAC Systems
Tianyao Ma, Aimin Tang, Yin Xu et al. (+3 more)
Affine frequency division multiplexing (AFDM) is a promising waveform for integrated sensing and communication (
ISAC). In AFDM systems, the complex gains, delays, and Doppler shifts are commonly estimated from the AFDM symbols carrying pilots and data simultaneously. In practice, however, the unknown data symbols and data-pilot coupling interference may render the
estimator mismatched to the true signal model. In this paper, we systematically characterize the parameter-estimation performance of AFDM-
ISAC systems under practical model misspecification. The main contributions are threefold. First, we extend the Cramér-Rao bound (CRB) for a general observation model that treats the data symbols as unknown, which generalizes existing AFDM CRB analyses and serves as the matched
benchmark for the subsequent analysis. Second, we identify two practical sources of misspecification, namely a covariance mismatch caused by insufficient pilot-data isolation and a combined covariance-and-mean mismatch caused by sequential single-target estimation, and derive the corresponding misspecified CRB (MCRB). Third, we characterize the pseudotrue parameters under different levels of prior knowledge, analyze the resulting estimation bias, and establish a lower bound (LB) on the mean square error (MSE). Simulation results validate the derived bounds and show that, under model misspecification, the CRB is overly optimistic while the MCRB and LB faithfully characterize the achievable accuracy. The comparison further reveals how these bounds vary with the pilot length and pilot power, providing useful guidance for pilot configuration.
Read the full abstract ▾
All authors Tianyao Ma, Aimin Tang, Yin Xu, Qu Luo, Dazhi He, Wenjun Zhang
Signal Processing
One Terahertz Full-Field Digital Back-Propagation over 3000 km
Eric Sillekens, Ruben S. Luis, Giammarco Di Sciullo et al. (+14 more)
We implement full-field digital back-propagation with a 1-THz receiver using 20 synchronous frequency-adjacent coherent receivers with digital stitching and a frequency-comb local oscillator. Relative to electronic dispersion compensation, per-channel DBP and full-field DBP achieve throughput gains of 2.2% and 5.4%, respectively.
Read the full abstract ▾
All authors Eric Sillekens, Ruben S. Luis, Giammarco Di Sciullo, Robert Emmerich, Carlo Centofanti, Daniele Orsuti, Robson A. Colares, Mindaugas Jarmolovičius, Ronit Sohanpal, Darli A. A. Melo, Luca Palmieri, Colja Schubert, Ronald Freund, Cristian Antonelli, Robert I. Killey, Polina Bayvel, Hideaki Furukawa
Image and Video Processing
Blasto-Net: An Explainable Multi-Task Learning for Blastocyst Segmentation, Grading, and Implantation Prediction
Zahra Asghari Varzaneh, Reza Khoshkangini, Magnus Johnsson et al. (+2 more)
This study introduces Blasto-Net, a multi-task deep learning model for comprehensive blastocyst analysis. The proposed model performs three tasks simultaneously in a single forward pass:
segmentation of the ZP, TE, and ICM compartments, morphological grading, and implantation outcome prediction. Accurate blastocyst analysis in in vitro fertilization (IVF) is challenging. The compartments often have similar textures but very different structures. To address these challenges, Blasto-Net employs an EfficientNet-B3 encoder with a UNet-style decoder enhanced by the Convolutional Block
Attention Module (CBAM) and a novel Edge-Aware
Attention Module (EAAM) to effectively capture both semantic and boundary information. To handle distinct compartment
topologies, the network employs specialized
segmentation heads and a composite region- and boundary-based loss. Additionally, Grad-CAM++ visualizations are used to verify the anatomical consistency of the model's predictions. Evaluated on a public HMC blastocyst
dataset, Blasto-Net achieves Dice scores of 94.93%, 91.60%, and 88.82% for ICM, ZP, and TE, respectively, alongside an implantation F1-score of 80.0%. These results demonstrate that Blasto-Net offers an accurate, interpretable, and efficient solution for automated blastocyst assessment, with strong potential to support clinical decision-making in IVF.
Read the full abstract ▾
All authors Zahra Asghari Varzaneh, Reza Khoshkangini, Magnus Johnsson, Thomas Ebner, Lars Johansson
Audio and Speech Processing
Fully Differentiable Neural Forced Alignment via Soft Dynamic Programming
Rotem Rousso, Eyal Cohen and Joseph Keshet
Recent advances in sequence modeling have significantly improved ASR systems, bringing them close to human-level recognition accuracy and enhancing robustness across diverse acoustic conditions and
languages. In contrast, Forced
Alignment has not experienced comparable progress, and traditional HMM-GMM frameworks remain widely adopted and highly competitive. To address this gap, we propose an end-to-end, fully differentiable neural architecture specifically designed for phoneme
alignment. The model consists of an encoder that processes the input signal and a decoder that produces
alignment decisions. The encoder is structured into two complementary branches: one dedicated to phoneme identity verification and the other to phoneme boundary detection. The decoder is implemented as a trainable module based on differentiable soft dynamic programming. The entire system is optimized end-to-end using a novel contrastive loss that encourages clear separation between steady-state phoneme regions and transition boundaries. The proposed approach outperforms the current state of the art in phoneme
alignment on hand-annotated English
benchmarks, achieves strong word-level generalization results, and demonstrates generalization on unseen
languages.
Read the full abstract ▾
Signal Processing · Cross-listed from cs.RO
Delta-Position Estimation-Based IMU Odometry: A Comparison of MLP and Kolmogorov-Arnold Networks
Osman Tokluoglu and Emin Keresteci
In this study, the learning-based inertial odometry problem is investigated using raw IMU measurements obtained from the EuRoC MAV
benchmark dataset. Instead of absolute position regression-a formulation that may lead to large constant errors-the models are trained to estimate the incremental displacement ({\Delta}p) over a fixed 50 ms sliding window, and the full trajectory is reconstructed through numerical integration. A standard Multi-Layer Perceptron (MLP) is compared with a Kolmogorov-Arnold Network (KAN) equipped with learnable B-spline activations. Although KAN has 6.9 times fewer parameters than MLP (8,444 versus 57,859), it produces a 44% lower error in terms of final cumulative drift on the test trajectory (9.61 m versus 17.23 m). In addition, KAN exhibits more stable behavior in terms of long-term error accumulation, with lower P_50 and P_90 cumulative drift values. These findings indicate that learnable B-spline-based activations have the potential to reduce error accumulation in the inertial odometry problem.
Read the full abstract ▾
Systems and Control
Control Barrier Function only Formation Tracking in Multi-Agent Systems
S. Saharsh and Pushpak Jagtap
This paper presents a real-time control framework for formation tracking of heterogeneous multi-
agent systems with non-linear dynamics. The proposed method formulates a single Control Barrier Function-like constraint within a quadratic optimization setting that addresses formation tracking. Relying on the relative information of neighboring
agents, the controller is designed to operate without the need for manual parameter tuning or a separate nominal formation controller. The leader-follower framework is validated through simulations of moving formations.
Read the full abstract ▾
Audio and Speech Processing
Does Translation-Enhanced Speech Encoder Pre-training Affect Speech LLMs?
Tomoya Mizumoto and Yusuke Fujita
Connecting a pre-trained
speech encoder to a Large
Language Model (LLM) is the standard architecture for building
Speech LLMs. However, a structural misalignment exists between the encoder and the LLM. Unlike encoders based on automatic
speech recognition, which often produce representations in separate
language-specific spaces, LLMs operate within a unified
language-agnostic space. A mechanism is required to align the encoder's
language-specific representations with the LLM's shared space. We argue that
speech translation provides a principled way to achieve this. Unlike monolingual transcription, translation requires the model to bridge different
languages and learn
language-agnostic representations. We experimentally evaluate the impact of incorporating translation objectives into
speech encoder pre-training. Our results demonstrate that translation-enhanced pre-training improves cross-modal integration and leads to superior performance across downstream
Speech LLM tasks.
Read the full abstract ▾
Audio and Speech Processing
Evaluating Japanese Dialect Robustness Across Speech and Text-based Large Language Models
Tomoya Mizumoto, Yusuke Fujita, Hao Shi et al. (+3 more)
Dialogue systems based on large
language models (LLMs) have advanced significantly in recent years. However, dialectal variation remains a major challenge, particularly for systems that process spoken input. LLM-based
speech language models (SLMs), which integrate LLMs with
speech processing components, show promise for spoken
language tasks, yet their ability to comprehend dialects has not been sufficiently studied. Moreover, it remains unclear how the dialectal understanding of the base LLM affects SLM performance. This study investigates the dialectal robustness of both LLMs and SLMs using Japanese dialects as a test case. We define robustness as the ratio of performance on dialectal versus standard inputs, enabling fair comparisons. Our experiments show that SLM robustness correlates with that of their text-based counterparts. Furthermore, training with dialectal data and fine-tuning the
speech encoder each improves robustness in SLMs.
Read the full abstract ▾
All authors Tomoya Mizumoto, Yusuke Fujita, Hao Shi, Lianbo Liu, Atsushi Kojima, Yui Sudo
Audio and Speech Processing
Adaptive Oscillatory Inductive Bias for Modeling Sharp Prosodic Dynamics in Diffusion-Based TTS
Sandipan Dhar, Nirmesh J. Shah, Ashishkumar P. Gudmalwar et al. (+1 more)
Diffusion-based text-to-
speech (TTS) models have achieved significant improvements in
speech quality. However, modeling sharp prosodic transitions and rapid pitch variations in expressive
speech remains challenging. Existing
diffusion-based TTS decoders commonly utilize periodic nonlinearities such as Snake activation function to capture harmonic structures, but this activation funcation provides limited adaptability when modeling abrupt amplitude and frequency variations. In this paper, we investigate the role of oscillatory inductive bias in
diffusion-based TTS decoders and introduce an adaptive oscillatory nonlinearity that enables controllable periodic modulation while maintaining signal stability through a linear bypass component. We refer the resulting TTS system as OscillaTTS. Experiments on the LJSpeech and Emotional
Speech Dataset show consistent improvements across objective and subjective evaluations, indicating improved modeling of expressive prosodic dynamics.
Read the full abstract ▾
All authors Sandipan Dhar, Nirmesh J. Shah, Ashishkumar P. Gudmalwar, Pankaj Wasnik
Signal Processing · Cross-listed from cs.IT
OAMP-Aided Joint Channel Estimation and Data Detection for ODDM Systems
Kehan Huang, Min Qiu, Akram Shafie et al. (+1 more)
In this work, to address the challenge of joint channel estimation and data detection (JED) for orthogonal delay-Doppler (DD) division multiplexing (ODDM) in doubly selective channels, we propose an orthogonal approximate message passing (OAMP)-aided JED (OAMP-JED) receiver. We first formulate a bilinear cross-domain JED model, which can be linearized into separate channel estimation and data detection subproblems. The proposed OAMP-JED receiver alternately executes two OAMP modules for these subproblems, effectively coupled through a variational noise term to account for model uncertainty. Leveraging OAMP's error orthogonality, we derive closed-form scalar-variance updates to enable efficient and principled soft information exchange between the modules, thereby mitigating error propagation during JED. Simulation results show that, for both uncoded and coded ODDM, OAMP-JED achieves a lower bit error rate (BER) than
benchmark schemes. Moreover, its BER performance closely approaches that of OAMP with perfect CSI.
Read the full abstract ▾
All authors Kehan Huang, Min Qiu, Akram Shafie, Jinhong Yuan
Audio and Speech Processing
CrossAccent-TTS: Cross-Lingual Accent-Intensity Controllable Text-to-Speech via Disentangled Speaker and Accent Representations
Ram Annamdevula, Ankit Tatawat, Ashishkumar P. Gudmalwar et al. (+2 more)
Accent conversion and controllability remain fundamental challenges in cross-lingual text-to-
speech (TTS), particularly for low-resource and phonetically diverse Indic
languages. While recent large
language model (LLM)-based TTS systems exhibit strong cross-lingual generalization, they provide limited explicit control over accent characteristics and intensity. In this paper, we propose CrossAccentTTS, a framework that enables both accent control and conversion while preserving speaker identity. Specifically, we introduce an Accent Intensity Controller (AIC) that injects weighted
language embeddings into the accent subspace, allowing smooth interpolation between accents and fine-grained modulation of accent strength at inference time. Experiments on the Indic
Multilingual and L2-arctic
datasets shows that CrossAccent-TTS achieves precise control of accent intensity, outperforming strong baselines in accent similarity and controllability by maintaining speaker similarity and naturalness.
Read the full abstract ▾
All authors Ram Annamdevula, Ankit Tatawat, Ashishkumar P. Gudmalwar, Nirmesh J. Shah, Pankaj Wasnik
Systems and Control
Conformal Recovery-Deadline Certificates for Runtime Assurance of Adapting Controllers
Alireza Shojaei
Runtime assurance (RTA) protects a safety-critical system by switching from an advanced controller to a verified safe controller when a monitored condition is violated. The standard latching rule, which trips on the first breach of the safe set and then coasts, is correct for a diverging controller but pathological for a capable online-adapting one. Such a controller is unsafe by design during a bounded recovery transient. It must excite the plant to identify the fault before it can correct it, so a latching shield trips on that transient and suppresses a controller that would have recovered. We introduce the conformal recovery-deadline certificate, a split-conformal, distribution-free, finite-sample upper bound on the adapting controller's recovery time that licenses delayed fallback with a coverage guarantee, backstopped by a verified monitor at a hard critical limit. The certified deadline discriminates capable from incapable controllers, keeping the recoverer autonomous while catching the diverger. The construction separates autonomy, governed by statistical coverage, from safety, governed by the verified backstop, as an instance of reliability-asymmetric design. We prove marginal coverage, a weighted extension that restores coverage under a known fault-distribution shift, and group-conditional Mondrian coverage. We demonstrate all three on two unrelated Simplex testbeds: a 6-DOF spacecraft attitude controller and a torque-controlled inverted pendulum. Both show the same suppression pathology and the same cure, making the certificate a domain-general mechanism rather than a single-system trick.
Read the full abstract ▾
Audio and Speech Processing · Cross-listed from cs.SD
Sarashina2.2-TTS: Tackling Kanji Polyphony in Japanese Speech Generation via Data Scaling and Targeted Data Synthesis
Lianbo Liu, Shiao Zhu, Kai Washizaki et al. (+10 more)
While large
language model (LLM)-based text-to-
speech (TTS) systems have achieved high-quality
speech synthesis, most existing systems focus on English and Chinese. Japanese, however, remains under-explored, and its unique linguistic challenges, such as widespread context-dependent kanji polyphony, have yet to be adequately tackled. Here we introduce Sarashina2.2-TTS (https://github.com/sbintuitions/sarashina2.2-tts), a Japanese-centric LLM-TTS system that tackles these challenges through a dual approach: data strategy and evaluation methodology. First, we scale training to approximately 361k hours of
speech, incorporating a balanced mix of Japanese and English data. Furthermore, we design a targeted data augmentation pipeline covering all 2,136 Joyo (regular-use) kanji designated by Japan's Agency for Cultural Affairs to efficiently address kanji polyphony disambiguation. Second, we introduce the Joyo Kanji Yomi
Benchmark (https://github.com/sbintuitions/JoyoKanji-Yomi-
Benchmark), covering all 2,136 Joyo kanji and their 4,378 readings. Alongside this
benchmark, we propose Kana-CER, a metric that compares synthesized
speech against reference readings in the kana space, eliminating orthographic variations to directly measure pronunciation correctness. Experiments demonstrate that our targeted data augmentation significantly improves reading accuracy. Overall, Sarashina2.2-TTS achieves state-of-the-art kanji-level reading accuracy and matches top baselines on general sentence-level pronunciation, while delivering the highest speaker similarity in zero-shot Japanese
speech synthesis. Furthermore, cross-lingual evaluation reveals that Sarashina2.2-TTS is the only system that maintains stable Japanese pronunciation regardless of the
prompt language, confirming that our balanced training approach improves cross-lingual robustness.
Read the full abstract ▾
All authors Lianbo Liu, Shiao Zhu, Kai Washizaki, Reo Yoneyama, Haesung Jeon, Mengjie Zhao, Yusuke Fujita, Hao Shi, Nao Yoshida, Yuan Gao, Roman Koshkin, Yukiya Hono, Yui Sudo