arXiv subjects

Jiang Wang

Publications and source records attributed to Jiang Wang.

At least 19 recordsLinked to original sources

arXiv2026

Exploring Efficient Waveform Diffusion Models for Foley Sound Generation

Recent advances in diffusion models have enabled high-fidelity Foley sound generation directly in the waveform space. Existing waveform diffusion models primarily rely on time-domain architectures, such as CNN-based U-Nets and DiffWave-style models, or frequency-domain Transformers modeling temporal dependencies. However, these systems are typically built with large model capacities and substantial computational costs, leaving compact and efficient waveform diffusion architectures largely underexplored. In this work, we introduce a Dual-Path (DP) architecture for waveform diffusion that performs dimension-wise self-attention along both subband and frame axes in the time-frequency domain. This DP design enables fine-grained temporal-spectral modeling while maintaining high efficiency. Based on the proposed DP backbone, we develop two variants: DP-DiT and DP-U-Net. Experiments on the DCASE and FSD-Kaggle2018 datasets demonstrate their superior performance. Notably, the 3M parameter variant achieves performance comparable to models with more than 50M parameters. Audio samples are available at https://samplesdemo.github.io/DP-Foley/.

eess.AS↗

arXiv2026

Twist Engineering for Reconfigurable Optical and Optoelectronic Devices

Reconfigurable optical and optoelectronic devices require compact tuning mechanisms capable of reshaping electronic, excitonic, polaritonic, and photonic responses without rebuilding the underlying nanostructure. Against this backdrop, twist has emerged as a powerful geometric degree of freedom that reconfigures interlayer coupling, momentum matching, symmetry, radiation channels, and chiral response by simply rotating adjacent two-dimensional layers or photonic lattices. In this Review, we survey twist-engineered optical and optoelectronic devices spanning van der Waals materials and photonic platforms. We first review the current landscape of twist-angle metrology, classifying existing characterization approaches into three complementary categories: direct structural imaging, methods based on moir\'e periodicity and morphological features, and techniques that infer the twist angle from spectroscopic or electronic responses. We then survey the principal technological routes for twist-angle control, including deterministic transfer and growth strategies, atomic force microscopy (AFM)-assisted manipulation, quantum twisting microscopy (QTM), microelectromechanical systems (MEMS), and emerging non-contact approaches, highlighting their respective capabilities, limitations, and prospects for programmable and scalable moir\'e photonic platforms. Finally, we discuss the future evolution of twist engineering from the fabrication of individual twisted structures toward dynamically reconfigurable, feedback-controlled, and manufacturable photonic systems. We further highlight MEMS-based rotation, piezoelectric actuation, and micro-LiDAR as representative enabling technologies and emerging applications within this broader landscape.

physics.optics↗

arXiv2026

What Do Neural Networks Learn for TDOA Estimation? A Cross-Architecture Probing Study

Neural networks outperform classical GCC-PHAT for Time-Difference-of-Arrival (TDOA) estimation in noise and reverberation, yet their internal strategy remains unexplored. To uncover it, we turn GCC-PHAT's mathematical steps into diagnostic targets, probing hidden layers of three architectures (MLP, CNN, Transformer) and complementing with gradient attribution and causal frequency masking. We find that cross-power computation consistently emerges across all architectures and conditions, while PHAT whitening, the defining step of GCC-PHAT, fails to emerge. Instead, networks learn a magnitude-aware frequency weighting that preserves per-frequency reliability information discarded by PHAT. This makes PHAT an information bottleneck: removing it from both classical and neural GCC pipelines improves performance under additive noise. On real-world reverberant data, PHAT remains the best classical weighting, but end-to-end networks achieve lower error by learning data-adaptive weighting.

cs.SD↗

arXiv2026

Fast-SDE: Efficient Single-Microphone Sound Source Distance Estimation in Reverberant Environments

Sound source distance estimation (SDE) is a critical capability in human-robot interaction. An inappropriate interaction distance not only reduces the reliability of speech acquisition and understanding, but also compromises the naturalness and comfort of the interaction. Most existing SDE methods rely on microphone arrays, however, multi-microphone systems typically require careful hardware synchronization, geometric calibration, and additional space and computational resources, which limits applicability to size-constrained and computability-limited embodied platforms. To alleviate these issues, we propose Fast-SDE, a lightweight single-microphone SDE framework that is suited for deployment on robot platforms with limited computational resources and strict size constraints. Specifically, Fast-SDE employs a subband-based backbone that decomposes the frequency axis into multiple subbands, rather than processing the entire spectrum with a wide full-band backbone. A shared subband encoder then maps each subband to a compact latent representation and learns the relationship between acoustic structure and time-frequency patterns. Finally, a lightweight regression head converts the fused subband representations into the estimated distance. Extensive simulation and real-world experiments demonstrate the merits of the proposed method. To benefit the broader research community, we have open-sourced our code at https://github.com/JiangWAV/FAST-SDE.

cs.SD↗

arXiv2026

ASAP: An Azimuth-Priority Strip-Based Search Approach to Planar Microphone Array DOA Estimation in 3D

Direction-of-arrival (DOA) estimation is an important task in microphone array processing and many downstream applications. The steered response power with phase transform (SRP-PHAT) method has been widely adopted for DOA estimation in recent years. However, accurate SRP-PHAT estimation in 3D scenarios requires evaluating steering responses over thousands of candidate directions, severely limiting real-time performance on resource-constrained platforms. This challenge becomes even more critical for planar arrays, which are widely used in robotics due to their structural simplicity. Motivated by the fact that azimuth estimation is usually more reliable than elevation estimation for most arrays, we propose ASAP, an azimuth-priority strip-based search approach to planar microphone array DOA estimation in 3D. In the first stage, ASAP performs coarse-to-fine region contraction within azimuthal strips to lock azimuth angles while retaining multiple maxima through spherical caps. In the second stage, it refines elevation along the great-circle arc between two close candidates. Extensive simulations and real-world experiments validate the efficiency and merits of the proposed method over existing approaches.

eess.AS↗

arXiv2026

Trust Your Memory: Verifiable Control of Smart Homes through Reinforcement Learning with Multi-dimensional Rewards

Large Language Models (LLMs) have become a key foundation for enabling personalized smart home experiences. While existing studies have explored how smart home assistants understand user queries to control devices in real time, their ability to perform memory-driven device control remains challenging from both evaluation and methodological perspectives. In terms of evaluation, existing benchmarks either focus on immediate device control or general open-domain memory retrieval tasks, and therefore cannot effectively evaluate a model's ability to perform memory-driven device control. Methodologically, while memory-driven device control can be approached using Reinforcement Learning, conventional RL methods generally rely on outcome-based supervision (i.e., whether the final task is achieved). This lack of intermediate feedback can lead to sub-optimal performance or local failures in fine-grained memory management tasks (adding, updating, deleting, and utilizing). To address these issues, we first release MemHomeLife, built from anonymized real-world long-term user interaction logs. To enable more fine-grained evaluation of different memory-related subtasks, we further construct MemHome, the first benchmark designed to systematically evaluate memory-driven device control in smart home scenarios.

cs.AI↗

arXiv2025

Unsupervised Single-Channel Audio Separation with Diffusion Source Priors

Single-channel audio separation aims to separate individual sources from a single-channel mixture. Most existing methods rely on supervised learning with synthetically generated paired data. However, obtaining high-quality paired data in real-world scenarios is often difficult. This data scarcity can degrade model performance under unseen conditions and limit generalization ability. To this end, in this work, we approach this problem from an unsupervised perspective, framing it as a probabilistic inverse problem. Our method requires only diffusion priors trained on individual sources. Separation is then achieved by iteratively guiding an initial state toward the solution through reconstruction guidance. Importantly, we introduce an advanced inverse problem solver specifically designed for separation, which mitigates gradient conflicts caused by interference between the diffusion prior and reconstruction guidance during inverse denoising. This design ensures high-quality and balanced separation performance across individual sources. Additionally, we find that initializing the denoising process with an augmented mixture instead of pure Gaussian noise provides an informative starting point that significantly improves the final performance. To further enhance audio prior modeling, we design a novel time-frequency attention-based network architecture that demonstrates strong audio modeling capability. Collectively, these improvements lead to significant performance gains, as validated across speech-sound event, sound event, and speech separation tasks.

eess.AS↗

arXiv2025

Multiple Source Localization via Local Radio Map Construction in Urban Environments

Accurately and efficiently addressing the multiple source localization (MSL) problem in urban environments, particularly designing a general method adaptable to an arbitrary number of sources, plays a crucial role in various fields such as cognitive radio (CR). Existing methods either fail to effectively utilize received signal strength (RSS) information without redundancy or lack generalizability to an arbitrary number of sources. In this work, we propose the Local Radio Map-Aided Multiple Source Localization Framework (LRM-MSL), which is a general method capable of handling an arbitrary number of sources. First, this framework constructs a local radio map that retains only the RSS information around the sources and binarizes it. Then, the connected component analysis tool is applied to the binarized map, which implements multi-source separation, transforming the MSL problem into a series of single-source localization (SSL) tasks. Finally, we design a numerical coordinate regression network to perform the SSL tasks. Since there is no publicly available RSS dataset for MSL, we construct the VaryTxLoc dataset to evaluate the performance of LRM-MSL. Experimental results demonstrate that LRM-MSL is an accurate and effective method, outperforming state-of-the-art approaches. Our code and dataset can be downloaded from https://github.com/hereis77/LRM-MSL.

eess.SP↗

arXiv2025

Unsupervised Single-Channel Speech Separation with Diffusion under Speaker-Embedding Guidance

Speech separation is a fundamental task in audio processing, typically addressed with fully supervised systems trained on paired mixtures. While effective, such systems typically rely on synthetic data pipelines, which may not reflect real-world conditions. Instead, we revisit the source-model paradigm, training a diffusion generative model solely on anechoic speech and formulating separation as a diffusion inverse problem. However, unconditional diffusion models lack speaker-level conditioning, they can capture local acoustic structure but produce temporally inconsistent speaker identities in separated sources. To address this limitation, we propose Speaker-Embedding guidance that, during the reverse diffusion process, maintains speaker coherence within each separated track while driving embeddings of different speakers further apart. In addition, we propose a new separation-oriented solver tailored for speech separation, and both strategies effectively enhance performance on the challenging task of unsupervised source-model-based speech separation, as confirmed by extensive experimental results. Audio samples and code are available at https://runwushi.github.io/UnSepDiff_demo.

eess.AS↗

arXiv2025

ACA-Net: Future Graph Learning for Logistical Demand-Supply Forecasting

Logistical demand-supply forecasting that evaluates the alignment between projected supply and anticipated demand, is essential for the efficiency and quality of on-demand food delivery platforms and serves as a key indicator for scheduling decisions. Future order distribution information, which reflects the distribution of orders in on-demand food delivery, is crucial for the performance of logistical demand-supply forecasting. Current studies utilize spatial-temporal analysis methods to model future order distribution information from serious time slices. However, learning future order distribution in online delivery platform is a time-series-insensitive problem with strong randomness. These approaches often struggle to effectively capture this information while remaining efficient. This paper proposes an innovative spatiotemporal learning model that utilizes only two graphs (ongoing and global) to learn future order distribution information, achieving superior performance compared to traditional spatial-temporal long-series methods. The main contributions are as follows: (1) The introduction of ongoing and global graphs in logistical demand-supply pressure forecasting compared to traditional long time series significantly enhances forecasting performance. (2) An innovative graph learning network framework using adaptive future graph learning and innovative cross attention mechanism (ACA-Net) is proposed to extract future order distribution information, effectively learning a robust future graph that substantially improves logistical demand-supply pressure forecasting outcomes. (3) The effectiveness of the proposed method is validated in real-world production environments.

cs.LG↗

arXiv2025

Single-Microphone-Based Sound Source Localization for Mobile Robots in Reverberant Environments

Accurately estimating sound source positions is crucial for robot audition. However, existing sound source localization methods typically rely on a microphone array with at least two spatially preconfigured microphones. This requirement hinders the applicability of microphone-based robot audition systems and technologies. To alleviate these challenges, we propose an online sound source localization method that uses a single microphone mounted on a mobile robot in reverberant environments. Specifically, we develop a lightweight neural network model with only 43k parameters to perform real-time distance estimation by extracting temporal information from reverberant signals. The estimated distances are then processed using an extended Kalman filter to achieve online sound source localization. To the best of our knowledge, this is the first work to achieve online sound source localization using a single microphone on a moving robot, a gap that we aim to fill in this work. Extensive experiments demonstrate the effectiveness and merits of our approach. To benefit the broader research community, we have open-sourced our code at https://github.com/JiangWAV/single-mic-SSL.

cs.RO↗

arXiv2025

Observability-Aware Active Calibration of Multi-Sensor Extrinsics for Ground Robots via Online Trajectory Optimization

Accurate calibration of sensor extrinsic parameters for ground robotic systems (i.e., relative poses) is crucial for ensuring spatial alignment and achieving high-performance perception. However, existing calibration methods typically require complex and often human-operated processes to collect data. Moreover, most frameworks neglect acoustic sensors, thereby limiting the associated systems' auditory perception capabilities. To alleviate these issues, we propose an observability-aware active calibration method for ground robots with multimodal sensors, including a microphone array, a LiDAR (exteroceptive sensors), and wheel encoders (proprioceptive sensors). Unlike traditional approaches, our method enables active trajectory optimization for online data collection and calibration, contributing to the development of more intelligent robotic systems. Specifically, we leverage the Fisher information matrix (FIM) to quantify parameter observability and adopt its minimum eigenvalue as an optimization metric for trajectory generation via B-spline curves. Through planning and replanning of robot trajectory online, the method enhances the observability of multi-sensor extrinsic parameters. The effectiveness and advantages of our method have been demonstrated through numerical simulations and real-world experiments. For the benefit of the community, we have also open-sourced our code and data at https://github.com/AISLAB-sustech/Multisensor-Calibration.

cs.RO↗

arXiv2025

Pulse duration dependence of material response in ultrafast laser-induced surface-penetrating nanovoids in fused silica

The focused ultrafast laser, with its ability to initiate nonlinear absorption in transparent materials, has emerged as one of the most effective approaches for micro-nano processing. In this study, we carried out research on the processing of high-aspect-ratio nanovoids on fused silica by using the single-pulse ultrafast Bessel beam. The thermodynamic response behaviors of the materials on surface and deep inside are found to exhibit pronounced disparities with the variation in laser pulse duration. As the pulse duration increases from 0.2 ps to 9.0 ps, the intensity of material ablation on silica surface exhibits a gradually decreasing trend, while for the void formation deep inside silica, the void diameter exhibits a trend of initial increase followed by decrease. In particular, no nanovoids are even induced deep inside when the pulse duration is 0.2 ps. The mechanism causing such differences is discussed and considered to be related to the peak intensity, group velocity dispersion, and plasma defocusing. By covering a polymer film on silica surface to influence the energy deposition, the thermomechanical response behaviors of the materials to laser pulse duration are modulated, and the material sputtering on nanovoid opening is suppressed. On this basis, surface-penetrating nanovoid arrays are fabricated on a 2-mm-thick silica sample using 2 ps Bessel beam. Given the nanovoid diameter of approximately 150 nm, the aspect ratio of the nanovoids on fused silica sample exceeds 13000:1. This outcome creates significant possibilities for the stealth dicing and processing of 3D photonic crystals, optical integrated devices, and nanofluidics.

physics.optics↗

arXiv2025

Single-Channel Target Speech Extraction Utilizing Distance and Room Clues

This paper aims to achieve single-channel target speech extraction (TSE) in enclosures utilizing distance clues and room information. Recent works have verified the feasibility of distance clues for the TSE task, which can imply the sound source's direct-to-reverberation ratio (DRR) and thus can be utilized for speech separation and TSE systems. However, such distance clue is significantly influenced by the room's acoustic characteristics, such as dimension and reverberation time, making it challenging for TSE systems that rely solely on distance clues to generalize across a variety of different rooms. To solve this, we suggest providing room environmental information (room dimensions and reverberation time) for distance-based TSE for better generalization capabilities. Especially, we propose a distance and environment-based TSE model in the time-frequency (TF) domain with learnable distance and room embedding. Results on both simulated and real collected datasets demonstrate its feasibility. Demonstration materials are available at https://runwushi.github.io/distance-room-demo-page/.

eess.AS↗

arXiv2025

Improved Extrinsic Calibration of Acoustic Cameras via Batch Optimization

Acoustic cameras have found many applications in practice. Accurate and reliable extrinsic calibration of the microphone array and visual sensors within acoustic cameras is crucial for fusing visual and auditory measurements. Existing calibration methods either require prior knowledge of the microphone array geometry or rely on grid search which suffers from slow iteration speed or poor convergence. To overcome these limitations, in this paper, we propose an automatic calibration technique using a calibration board with both visual and acoustic markers to identify each microphone position in the camera frame. We formulate the extrinsic calibration problem (between microphones and the visual sensor) as a nonlinear least squares problem and employ a batch optimization strategy to solve the associated problem. Extensive numerical simulations and realworld experiments show that the proposed method improves both the accuracy and robustness of extrinsic parameter calibration for acoustic cameras, in comparison to existing methods. To benefit the community, we open-source all the codes and data at https://github.com/AISLAB-sustech/AcousticCamera.

cs.RO↗

arXiv2025

GaussDB-Global: A Geographically Distributed Database System

Geographically distributed database systems use remote replication to protect against regional failures. These systems are sensitive to severe latency penalties caused by centralized transaction management, remote access to sharded data, and log shipping over long distances. To tackle these issues, we present GaussDB-Global, a sharded geographically distributed database system with asynchronous replication, for OLTP applications. To tackle the transaction management bottleneck, we take a decentralized approach using synchronized clocks. Our system can seamlessly transition between centralized and decentralized transaction management, providing efficient fault tolerance and streamlining deployment. To alleviate the remote read and log shipping issues, we support reads on asynchronous replicas with strong consistency, tunable freshness guarantees, and dynamic load balancing. Our experimental results on a geographically distributed cluster show that our approach provides up to 14x higher read throughput, and 50% more TPC-C throughput compared to our baseline.

cs.DB↗

arXiv2024

Conditional Text-to-Image Generation with Reference Guidance

Text-to-image diffusion models have demonstrated tremendous success in synthesizing visually stunning images given textual instructions. Despite remarkable progress in creating high-fidelity visuals, text-to-image models can still struggle with precisely rendering subjects, such as text spelling. To address this challenge, this paper explores using additional conditions of an image that provides visual guidance of the particular subjects for diffusion models to generate. In addition, this reference condition empowers the model to be conditioned in ways that the vocabularies of the text tokenizer cannot adequately represent, and further extends the model's generalization to novel capabilities such as generating non-English text spellings. We develop several small-scale expert plugins that efficiently endow a Stable Diffusion model with the capability to take different references. Each plugin is trained with auxiliary networks and loss functions customized for applications such as English scene-text generation, multi-lingual scene-text generation, and logo-image generation. Our expert plugins demonstrate superior results than the existing methods on all tasks, each containing only 28.55M trainable parameters.

cs.CV↗

arXiv2024

STTM: A New Approach Based Spatial-Temporal Transformer And Memory Network For Real-time Pressure Signal In On-demand Food Delivery

On-demand Food Delivery (OFD) services have become very common around the world. For example, on the Ele.me platform, users place more than 15 million food orders every day. Predicting the Real-time Pressure Signal (RPS) is crucial for OFD services, as it is primarily used to measure the current status of pressure on the logistics system. When RPS rises, the pressure increases, and the platform needs to quickly take measures to prevent the logistics system from being overloaded. Usually, the average delivery time for all orders within a business district is used to represent RPS. Existing research on OFD services primarily focuses on predicting the delivery time of orders, while relatively less attention has been given to the study of the RPS. Previous research directly applies general models such as DeepFM, RNN, and GNN for prediction, but fails to adequately utilize the unique temporal and spatial characteristics of OFD services, and faces issues with insufficient sensitivity during sudden severe weather conditions or peak periods. To address these problems, this paper proposes a new method based on Spatio-Temporal Transformer and Memory Network (STTM). Specifically, we use a novel Spatio-Temporal Transformer structure to learn logistics features across temporal and spatial dimensions and encode the historical information of a business district and its neighbors, thereby learning both temporal and spatial information. Additionally, a Memory Network is employed to increase sensitivity to abnormal events. Experimental results on the real-world dataset show that STTM significantly outperforms previous methods in both offline experiments and the online A/B test, demonstrating the effectiveness of this method.

cs.LG↗