arXiv subjects

Xueliang Zhang

Publications and source records attributed to Xueliang Zhang.

At least 19 recordsLinked to original sources

arXiv2026

PhaseGAN: High-Fidelity Vocoder via Decoupled Amplitude and GAN-Driven Phase Reconstruction

A vocoder is a pivotal component of modern text-to-speech (TTS) systems. Despite the significant progress of neural network-based vocoders, accurate phase reconstruction remains the main challenge limiting both audio quality and modeling efficiency. We introduce PhaseGAN, a lightweight vocoder that addresses this limitation through a "mel $\rightarrow$ Amplitude $\rightarrow$ Phase" reconstruction pipeline. By reconstructing amplitude and phase spectra via distinct methodologies, the proposed PhaseGAN outperforms state-of-the-art baselines while utilizing fewer model parameters and reduced computational requirements. The compact version generates high-fidelity audio with approximately 500K parameters and 1 GMAC computational load, making it highly suitable for real-time applications on edge devices. In addition, our approach exhibits exceptional musical audio synthesis capabilities despite no training on musical data, illustrating unprecedented cross-domain generalization. See https://github.com/phasegan/phasegan-audio-demo for demos of our work.

cs.SD↗

arXiv2026

Complete Structural Determination of Mesostructural Dodecagonal Quasicrystalline Particles

Quasicrystals have revolutionized our understanding of order in solids by demonstrating exotic structural and physicochemical properties with diverse potential applications. Despite the development of various theoretical models and experimental techniques to describe quasicrystal structures, the precise determination of local three dimensional (3D) arrangements of constituent atoms, or of secondary building units such as clusters or micelles, remains elusive. This challenge is particularly acute in self assembled soft matter quasicrystalline systems, where the complex assembly of molecular groups introduces additional defects and structural modulations. Herein, we report the first complete structural determination of self-assembled mesostructural dodecagonal quasicrystalline particles. Employing advanced electron tomography, combined with dedicated structural tracing and processing workflows, the 3D coordinates of all nodal sites were extracted. This approach reveals that the actual structure deviates from the conventionally assumed tetrahedral close packing geometry, exhibiting diverse coordination environments and displacive fluctuations. We identified and quantified rotational intergrowths arising from node exchange, as well as various defects and disorder, with these features discernible only through 3D analysis. Additionally, we propose a simplified two-layer stacking of isomorphic hexagonal model to form dodecagonal quasicrystal. This work advances our understanding of soft-matter dodecagonal quasicrystals and paves the way for detailed structural elucidation of self-assembled systems.

cond-mat.mes-hall↗

arXiv2026

Remote Sensing Image Super-Resolution for Imbalanced Textures: A Texture-Aware Diffusion Framework

Generative diffusion priors have recently achieved state-of-the-art performance in natural image super-resolution, demonstrating a powerful capability to synthesize photorealistic details. However, their direct application to remote sensing image super-resolution (RSISR) reveals significant shortcomings. Unlike natural images, remote sensing images exhibit a unique texture distribution where ground objects are globally stochastic yet locally clustered, leading to highly imbalanced textures. This imbalance severely hinders the model's spatial perception. To address this, we propose TexADiff, a novel framework that begins by estimating a Relative Texture Density Map (RTDM) to represent the texture distribution. TexADiff then leverages this RTDM in three synergistic ways: as an explicit spatial conditioning to guide the diffusion process, as a loss modulation term to prioritize texture-rich regions, and as a dynamic adapter for the sampling schedule. These modifications are designed to endow the model with explicit texture-aware capabilities. Experiments demonstrate that TexADiff achieves superior or competitive quantitative metrics. Furthermore, qualitative results show that our model generates faithful high-frequency details while effectively suppressing texture hallucinations. This improved reconstruction quality also results in significant gains in downstream task performance. The source code of our method can be found at https://github.com/ZezFuture/TexAdiff.

cs.CV↗

arXiv2026

OpenEarth-Agent: From Tool Calling to Tool Creation for Open-Environment Earth Observation

Earth Observation (EO) is essential for perceiving dynamic land surface changes, yet deploying autonomous EO in open environments is hindered by the immense diversity of multi-source data and heterogeneous tasks. While remote sensing agents have emerged to streamline EO workflows, existing tool-calling agents are confined to closed environments. They rely on pre-defined tools and are restricted to narrow scope, limiting their generalization to the diverse data and tasks. To overcome these limitations, we introduce OpenEarth-Agent, the first tool-creation agent framework tailored for open-environment EO. Rather than calling predefined tools, OpenEarth-Agent employs adaptive workflow planning and tool creation to generalize to unseen data and tasks. This adaptability is bolstered by an open-ended integration of multi-stage tools and cross-domain knowledge bases, enabling robust execution in the entire EO pipeline across multiple application domains. To comprehensively evaluate EO agents in open environments, we propose OpenEarth-Bench, a novel benchmark comprising 596 real-world, full-pipeline cases across seven application domains, explicitly designed to assess agents' adaptive planning and tool creation capabilities. Only essential pre-trained model tools are provided in this benchmark, devoid of any other predefined task-specific tools. Extensive experiments demonstrate that OpenEarth-Agent successfully masters full-pipeline EO across multiple domains in the open environment. Notably, on the cross-benchmark Earth-Bench, our tool-creating agent equipped with 6 essential pre-trained models achieves performance comparable to tool-calling agents relying on 104 specialized tools, and significantly outperforms them when provided with the complete toolset. In several cases, the created tools exhibit superior robustness to data anomalies compared to human-engineered counterparts.

cs.CV↗

arXiv2025

FarSLIP: Discovering Effective CLIP Adaptation for Fine-Grained Remote Sensing Understanding

As CLIP's global alignment limits its ability to capture fine-grained details, recent efforts have focused on enhancing its region-text alignment. However, current remote sensing (RS)-specific CLIP variants still inherit this limited spatial awareness. We identify two key limitations behind this: (1) current RS image-text datasets generate global captions from object-level labels, leaving the original object-level supervision underutilized; (2) despite the success of region-text alignment methods in general domain, their direct application to RS data often leads to performance degradation. To address these, we construct the first multi-granularity RS image-text dataset, MGRS-200k, featuring rich object-level textual supervision for RS region-category alignment. We further investigate existing fine-grained CLIP tuning strategies and find that current explicit region-text alignment methods, whether in a direct or indirect way, underperform due to severe degradation of CLIP's semantic coherence. Building on these, we propose FarSLIP, a Fine-grained Aligned RS Language-Image Pretraining framework. Rather than the commonly used patch-to-CLS self-distillation, FarSLIP employs patch-to-patch distillation to align local and global visual cues, which improves feature discriminability while preserving semantic coherence. Additionally, to effectively utilize region-text supervision, it employs simple CLS token-based region-category alignment rather than explicit patch-level alignment, further enhancing spatial awareness. FarSLIP features improved fine-grained vision-language alignment in RS domain and sets a new state of the art not only on RS open-vocabulary semantic segmentation, but also on image-level tasks such as zero-shot classification and image-text retrieval. Our dataset, code, and models are available at https://github.com/NJU-LHRS/FarSLIP.

cs.CV↗

arXiv2025

Two-stage Audio-Visual Target Speaker Extraction System for Real-Time Processing On Edge Device

Audio-Visual Target Speaker Extraction (AVTSE) aims to isolate a target speaker's voice in a multi-speaker environment with visual cues as auxiliary. Most of the existing AVTSE methods encode visual and audio features simultaneously, resulting in extremely high computational complexity and making it impractical for real-time processing on edge devices. To tackle this issue, we proposed a two-stage ultra-compact AVTSE system. Specifically, in the first stage, a compact network is employed for voice activity detection (VAD) using visual information. In the second stage, the VAD results are combined with audio inputs to isolate the target speaker's voice. Experiments show that the proposed system effectively suppresses background noise and interfering voices while spending little computational resources.

cs.SD↗

arXiv2025

Loud-loss: A Perceptually Motivated Loss Function for Speech Enhancement Based on Equal-Loudness Contours

The mean squared error (MSE) is a ubiquitous loss function for speech enhancement, but its problem is that the error cannot reflect the auditory perception quality. This is because MSE causes models to over-emphasize low-frequency components which has high energy, leading to the inadequate modeling of perceptually important high-frequency information. To overcome this limitation, we propose a perceptually-weighted loss function grounded in psychoacoustic principles. Specifically, it leverages equal-loudness contours to assign frequency-dependent weights to the reconstruction error, thereby penalizing deviations in a way aligning with human auditory sensitivity. The proposed loss is model-agnostic and flexible, demonstrating strong generality. Experiments on the VoiceBank+DEMAND dataset show that replacing MSE with our loss in a GTCRN model elevates the WB-PESQ score from 2.17 to 2.93-a significant improvement in perceptual quality.

cs.SD↗

arXiv2025

Listen to Extract: Onset-Prompted Target Speaker Extraction

We propose listen to extract (LExt), a highly-effective while extremely-simple algorithm for monaural target speaker extraction (TSE). Given an enrollment utterance of a target speaker, LExt aims at extracting the target speaker from the speaker's mixed speech with other speakers. For each mixture, LExt concatenates an enrollment utterance of the target speaker to the mixture signal at the waveform level, and trains deep neural networks (DNN) to extract the target speech based on the concatenated mixture signal. The rationale is that, this way, an artificial speech onset is created for the target speaker and it could prompt the DNN (a) which speaker is the target to extract; and (b) spectral-temporal patterns of the target speaker that could help extraction. This simple approach produces strong TSE performance on multiple public TSE datasets including WSJ0-2mix, WHAM! and WHAMR!.

eess.AS↗

arXiv2025

Spin-polarized chiral ZnIn2S4 for targeted solar-driven CO2 reduction to acetic acid

Acetic acid, an important industrial chemical, is a key target product for CO2 reduction due to its dual role in carbon utilization and chemical feedstock supply. Although photocatalytic CO2 reduction (PCCR) can generate acetic acid alongside other multicarbon products, its yield is typically low, limited by competing reactions and inefficient C-C coupling. Herein, we report a chiral mesostructured ZnIn2S4 (CMZI) photocatalyst that achieves a remarkable acetic acid yield of 962 {umol g-1 h-1 with a high selectivity of 97.3 %. This yield is ten times higher than the current highest reported value, while attaining state-of-the-art selectivity10. The remarkable productivity arises from synergistic effect between chiral structure and sulfur (S) sites of CMZI. Chirality-induced spin polarization in CMZI stabilizes the key triplet OCCO intermediate, significantly promoting C-C coupling efficiency. Theoretical calculations reveal that the S sites on {102} crystal facets of ZnIn2S4 exhibit thermodynamic and kinetic preferences for acetic acid formation. This work offers critical insights into catalytic strategies for CO2 reduction toward the efficient and scalable synthesis of various multicarbon products.

cond-mat.mtrl-sci↗

arXiv2025

Quality-Driven Curation of Remote Sensing Vision-Language Data via Learned Scoring Models

Vision-Language Models (VLMs) have demonstrated great potential in interpreting remote sensing (RS) images through language-guided semantic. However, the effectiveness of these VLMs critically depends on high-quality image-text training data that captures rich semantic relationships between visual content and language descriptions. Unlike natural images, RS lacks large-scale interleaved image-text pairs from web data, making data collection challenging. While current approaches rely primarily on rule-based methods or flagship VLMs for data synthesis, a systematic framework for automated quality assessment of such synthetically generated RS vision-language data is notably absent. To fill this gap, we propose a novel score model trained on large-scale RS vision-language preference data for automated quality assessment. Our empirical results demonstrate that fine-tuning CLIP or advanced VLMs (e.g., Qwen2-VL) with the top 30% of data ranked by our score model achieves superior accuracy compared to both full-data fine-tuning and CLIP-score-based ranking approaches. Furthermore, we demonstrate applications of our scoring model for reinforcement learning (RL) training and best-of-N (BoN) test-time scaling, enabling significant improvements in VLM performance for RS tasks. Our code, model, and dataset are publicly available

cs.CV↗

arXiv2025

Spatial-Temporal-Spectral Unified Modeling for Remote Sensing Dense Prediction

The proliferation of multi-source remote sensing data has propelled the development of deep learning for dense prediction, yet significant challenges in data and task unification persist. Current deep learning architectures for remote sensing are fundamentally rigid. They are engineered for fixed input-output configurations, restricting their adaptability to the heterogeneous spatial, temporal, and spectral dimensions inherent in real-world data. Furthermore, these models neglect the intrinsic correlations among semantic segmentation, binary change detection, and semantic change detection, necessitating the development of distinct models or task-specific decoders. This paradigm is also constrained to a predefined set of output semantic classes, where any change to the classes requires costly retraining. To overcome these limitations, we introduce the Spatial-Temporal-Spectral Unified Network (STSUN) for unified modeling. STSUN can adapt to input and output data with arbitrary spatial sizes, temporal lengths, and spectral bands by leveraging their metadata for a unified representation. Moreover, STSUN unifies disparate dense prediction tasks within a single architecture by conditioning the model on trainable task embeddings. Similarly, STSUN facilitates flexible prediction across multiple set of semantic categories by integrating trainable category embeddings as metadata. Extensive experiments on multiple datasets with diverse Spatial-Temporal-Spectral configurations in multiple scenarios demonstrate that a single STSUN model effectively adapts to heterogeneous inputs and outputs, unifying various dense prediction tasks and diverse semantic class predictions. The proposed approach consistently achieves state-of-the-art performance, highlighting its robustness and generalizability for complex remote sensing applications.

cs.CV↗

arXiv2025

Multi-Channel Acoustic Echo Cancellation Based on Direction-of-Arrival Estimation

Acoustic echo cancellation (AEC) is an important speech signal processing technology that can remove echoes from microphone signals to enable natural-sounding full-duplex speech communication. While single-channel AEC is widely adopted, multi-channel AEC can leverage spatial cues afforded by multiple microphones to achieve better performance. Existing multi-channel AEC approaches typically combine beamforming with deep neural networks (DNN). This work proposes a two-stage algorithm that enhances multi-channel AEC by incorporating sound source directional cues. Specifically, a lightweight DNN is first trained to predict the sound source directions, and then the predicted directional information, multi-channel microphone signals, and single-channel far-end signal are jointly fed into an AEC network to estimate the near-end signal. Evaluation results show that the proposed algorithm outperforms baseline approaches and exhibits robust generalization across diverse acoustic environments.

cs.SD↗

arXiv2025

ARiSE: Auto-Regressive Multi-Channel Speech Enhancement

We propose ARiSE, an auto-regressive algorithm for multi-channel speech enhancement. ARiSE improves existing deep neural network (DNN) based frame-online multi-channel speech enhancement models by introducing auto-regressive connections, where the estimated target speech at previous frames is leveraged as extra input features to help the DNN estimate the target speech at the current frame. The extra input features can be derived from (a) the estimated target speech in previous frames; and (b) a beamformed mixture with the beamformer computed based on the previous estimated target speech. On the other hand, naively training the DNN in an auto-regressive manner is very slow. To deal with this, we propose a parallel training mechanism to speed up the training. Evaluation results in noisy-reverberant conditions show the effectiveness and potential of the proposed algorithms.

eess.AS↗

arXiv2025

Room Impulse Response as a Prompt for Acoustic Echo Cancellation

Data-driven acoustic echo cancellation (AEC) methods, predominantly trained on synthetic or constrained real-world datasets, encounter performance declines in unseen echo scenarios, especially in real environments where echo paths are not directly observable. Our proposed method counters this limitation by integrating room impulse response (RIR) as a pivotal training prompt, aiming to improve the generalization of AEC models in such unforeseen conditions. We also explore four RIR prompt fusion methods. Comprehensive evaluations, including both simulated RIR under unknown conditions and recorded RIR in real, demonstrate that the proposed approach significantly improves performance compared to baseline models. These results substantiate the effectiveness of our RIR-guided approach in strengthening the model's generalization capabilities.

cs.SD↗

arXiv2025

Transforming Weather Data from Pixel to Latent Space

The increasing impact of climate change and extreme weather events has spurred growing interest in deep learning for weather research. However, existing studies often rely on weather data in pixel space, which presents several challenges such as smooth outputs in model outputs, limited applicability to a single pressure-variable subset (PVS), and high data storage and computational costs. To address these challenges, we propose a novel Weather Latent Autoencoder (WLA) that transforms weather data from pixel space to latent space, enabling efficient weather task modeling. By decoupling weather reconstruction from downstream tasks, WLA improves the accuracy and sharpness of weather task model results. The incorporated Pressure-Variable Unified Module transforms multiple PVS into a unified representation, enhancing the adaptability of the model in multiple weather scenarios. Furthermore, weather tasks can be performed in a low-storage latent space of WLA rather than a high-storage pixel space, thus significantly reducing data storage and computational costs. Through extensive experimentation, we demonstrate its superior compression and reconstruction performance, enabling the creation of the ERA5-latent dataset with unified representations of multiple PVS from ERA5 data. The compressed full PVS in the ERA5-latent dataset reduces the original 244.34 TB of data to 0.43 TB. The downstream task further demonstrates that task models can apply to multiple PVS with low data costs in latent space and achieve superior performance compared to models in pixel space. Code, ERA5-latent data, and pre-trained models are available at https://anonymous.4open.science/r/Weather-Latent-Autoencoder-8467.

cs.CV↗

arXiv2024

Attention-Enhanced Short-Time Wiener Solution for Acoustic Echo Cancellation

Acoustic Echo Cancellation (AEC) is an essential speech signal processing technology that removes echoes from microphone inputs to facilitate natural-sounding full-duplex communication. Currently, deep learning-based AEC methods primarily focus on refining model architectures, frequently neglecting the incorporation of knowledge from traditional filter theory. This paper presents an innovative approach to AEC by introducing an attention-enhanced short-time Wiener solution. Our method strategically harnesses attention mechanisms to mitigate the impact of double-talk interference, thereby optimizing the efficiency of knowledge utilization. The derivation of the short-term Wiener solution, which adapts classical Wiener solutions to finite input causality, integrates established insights from filter theory into this method. The experimental outcomes corroborate the effectiveness of our proposed approach, surpassing other baseline models in performance and generalization. The official code is available at https://github.com/ZhaoF-i/ASTWS-AEC

cs.SD↗

arXiv2024

Robust Target Speaker Direction of Arrival Estimation

In multi-speaker environments the direction of arrival (DOA) of a target speaker is key for improving speech clarity and extracting target speaker's voice. However, traditional DOA estimation methods often struggle in the presence of noise, reverberation, and particularly when competing speakers are present. To address these challenges, we propose RTS-DOA, a robust real-time DOA estimation system. This system innovatively uses the registered speech of the target speaker as a reference and leverages full-band and sub-band spectral information from a microphone array to estimate the DOA of the target speaker's voice. Specifically, the system comprises a speech enhancement module for initially improving speech quality, a spatial module for learning spatial information, and a speaker module for extracting voiceprint features. Experimental results on the LibriSpeech dataset demonstrate that our RTS-DOA system effectively tackles multi-speaker scenarios and established new optimal benchmarks.

cs.SD↗

arXiv2024

StreamAdapter: Efficient Test Time Adaptation from Contextual Streams

In-context learning (ICL) allows large language models (LLMs) to adapt to new tasks directly from the given demonstrations without requiring gradient updates. While recent advances have expanded context windows to accommodate more demonstrations, this approach increases inference costs without necessarily improving performance. To mitigate these issues, We propose StreamAdapter, a novel approach that directly updates model parameters from context at test time, eliminating the need for explicit in-context demonstrations. StreamAdapter employs context mapping and weight absorption mechanisms to dynamically transform ICL demonstrations into parameter updates with minimal additional parameters. By reducing reliance on numerous in-context examples, StreamAdapter significantly reduce inference costs and allows for efficient inference with constant time complexity, regardless of demonstration count. Extensive experiments across diverse tasks and model architectures demonstrate that StreamAdapter achieves comparable or superior adaptation capability to ICL while requiring significantly fewer demonstrations. The superior task adaptation and context encoding capabilities of StreamAdapter on both language understanding and generation tasks provides a new perspective for adapting LLMs at test time using context, allowing for more efficient adaptation across scenarios and more cost-effective inference

cs.CL↗