arXiv subjects

Ruoyi Zhang

Publications and source records attributed to Ruoyi Zhang.

At least 19 recordsLinked to original sources

arXiv2026

Fish Audio S2 Technical Report

We introduce Fish Audio S2, an open-sourced text-to-speech system featuring multi-speaker, multi-turn generation, and, most importantly, instruction-following control via natural-language descriptions. To scale training, we develop a multi-stage training recipe together with a staged data pipeline covering video captioning and speech captioning, voice-quality assessment, and reward modeling. To push the frontier of open-source TTS, we release our model weights, fine-tuning code, and an SGLang-based inference engine. The inference engine is production-ready for streaming, achieving an RTF of 0.195 and a time-to-first-audio below 100 ms.Our code and weights are available on GitHub (https://github.com/fishaudio/fish-speech) and Hugging Face (https://huggingface.co/fishaudio/s2-pro). We highly encourage readers to visit https://fish.audio to try custom voices.

cs.SD↗

arXiv2026

Physics Encoded Spatial and Temporal Generative Adversarial Network for Tropical Cyclone Image Super-resolution

High-resolution satellite imagery is indispensable for tracking the genesis, intensification, and trajectory of tropical cyclones (TCs). However, existing deep learning-based super-resolution (SR) methods often treat satellite image sequences as generic videos, neglecting the underlying atmospheric physical laws governing cloud motion. To address this, we propose a Physics Encoded Spatial and Temporal Generative Adversarial Network (PESTGAN) for TC image super-resolution. Specifically, we design a disentangled generator architecture incorporating a PhyCell module, which approximates the vorticity equation via constrained convolutions and encodes the resulting approximate physical dynamics as implicit latent representations to separate physical dynamics from visual textures. Furthermore, a dual-discriminator framework is introduced, employing a temporal discriminator to enforce motion consistency alongside spatial realism. Experiments on the Digital Typhoon dataset for 4$\times$ upscaling demonstrate that PESTGAN establishes a better performance in structural fidelity and perceptual quality. While maintaining competitive pixel-wise accuracy compared to existing approaches, our method significantly excels in reconstructing meteorologically plausible cloud structures with superior physical fidelity.

cs.CV↗

arXiv2026

A Tale of Two Dust Disks in Our Milky Way

Cosmic dust plays a vital role in stellar and galactic formation and evolution, but its three-dimensional structure in the Milky Way has remained unclear due to insufficient precise reddening and distance measurements. Although early studies typically adopted a single-disk model, we detect two distinct components at Galactocentric distances of 5-14 kpc, enabled by photometric, spectroscopic, and astrometric measurements of over 5 million stars. The thin dust disk's scale height increases radially from 60 to 200 pc, while the thick disk grows from 300 to 800 pc. For the first time, we find the thin and thick dust disk correlates spatially with molecular and atomic hydrogen disk, respectively. The thin, thick, and combined disks have scale lengths of 9.6+1.2-1.1 kpc, 4.2+0.4-0.3 kpc, and 6.6+0.3-0.3 kpc, respectively. The gas-to-dust ratio shows an exponential radial gradient, increasing from around 60 at 5 kpc to around 470 at 14 kpc. These findings provide new insights into dust morphology in the Galaxy and raise fundamental questions that require further investigation.

astro-ph.GA↗

arXiv2025

Recalibration of the Landolt UBVRI Standard Stars and the Generation of 5.4 Million New UBVRI Standard Stars using LAMOST and Gaia

We present an independent validation and recalibration of the Landolt 2013 (celestial equator and $δ\sim -50^\circ$) and 2016 ($δ\sim -50^\circ$) standard stars in the Johnson $UBV$ and Kron-Cousins $RI$ systems, using tens of thousands of XPSP data from the BEst STar (BEST) database. Our analysis reveals an overall zero-point offset between the 2016 and 2013 datasets. We further identify zero-point offsets for each standard field, ranging from 5 -- 14 mmag across all $UBVRI$ bands, with correlations between offsets in different bands. Additionally, we confirm the spatial structures up to 7 -- 10 mmag in the $BVRI$ bands. We also find that spatial structures are similar across bands for the same field, and similar across different fields for the same band. These similarities may arise from the averaged flat-fields from each observing run. The recalibrated results are consistent with the XPSP data within 48 mmag in the $U$ band, 11 mmag in the $B$ band, and 5 -- 6 mmag in the $VRI$ bands in the brightness $G<16$. Furthermore, based on stellar atmospheric parameters from LAMOST DR12 and Gaia DR3 photometry, along with the XPSP data, we derive temperature- and extinction-dependent extinction coefficients for the $UBVRI$ bands as well as a LAMOST \& Gaia-based catalog of 5.4 million standard stars in the $UBVRI$ bands, for which the U-band photometry of the vast majority of sources exhibits significantly higher precision than XPSP. The recalibrated Landolt standard stars and LAMOST \& Gaia-based standard stars will be available on the BEST website (https://nadc.china-vo.org/data/best/) and (https://doi.org/10.12149/101704).

astro-ph.SR↗

arXiv2025

Stellar Loci. IX. Estimation of Stellar Parameters from CSST-like Photometry

The China Space Station Telescope (CSST) will conduct a deep and wide imaging survey in the NUV-, u-, g-, r-, i-, z-, and y-bands. In this work, using theoretical data synthesized from the BOSZ spectra of Bohlin et al. (2017), along with observational data constructed from different sources, we present two methods for estimating stellar parameters from CSST-like photometry. One approach is to estimate metallicity [M/H] and surface gravity log g simultaneously by using the metallicity- and log g-dependent stellar loci. Tests with theoretical data (without photometric errors) result in precisions of 0.088 dex and 0.083 dex for [M/H] and log g, respectively. With 0.01 mag photometric errors, precision is degraded by about a factor of two, due to degeneracy in [M/H] and log g. Tests with observational data, although with larger photometric errors, result in precisions of 0.10 dex and 0.39 dex for [Fe/H] and log g, respectively, thanks to the strong correlation between stellar colors and log g in real data. The other approach is the giant-dwarf loci method to obtain classifications and metallicity estimates. With the same observational data, it achieves a better [Fe/H] precision of 0.084 dex, due to the stronger constraints imposed on log g. The method also performs well in distinguishing giants from dwarfs, particularly for red or metal-poor giants. This work demonstrates the clear potential of the CSST data, paving the way for stellar-parameter estimates for many billions of stars.

astro-ph.SR↗

arXiv2025

FCPE: A Fast Context-based Pitch Estimation Model

Pitch estimation (PE) in monophonic audio is crucial for MIDI transcription and singing voice conversion (SVC), but existing methods suffer significant performance degradation under noise. In this paper, we propose FCPE, a fast context-based pitch estimation model that employs a Lynx-Net architecture with depth-wise separable convolutions to effectively capture mel spectrogram features while maintaining low computational cost and robust noise tolerance. Experiments show that our method achieves 96.79\% Raw Pitch Accuracy (RPA) on the MIR-1K dataset, on par with the state-of-the-art methods. The Real-Time Factor (RTF) is 0.0062 on a single RTX 4090 GPU, which significantly outperforms existing algorithms in efficiency. Code is available at https://github.com/CNChTu/FCPE.

cs.SD↗

arXiv2025

An all-sky 3D dust map Based on Gaia and LAMOST

We present a comprehensive 3D dust reddening map covering the entire Milky Way, constructed by combining reddening estimates based on LAMOST low-resolution spectra (E(B$-$V)$_{\rm LAMOST}$) with those derived from $Gaia$ XP spectra (E(B$-$V)$_{\rm XP}$), along with revised $Gaia$ distances. E(B$-$V)$_{\rm LAMOST}$ values of $\sim$ 4.6 million unique sources were obtained with the standard-pair analysis using LAMOST DR11 stellar parameters and synthesized $B/V$-band photometry from $Gaia$ XP spectra, showing a typical precision of $\sim$ 0.01 mag. The E(B$-$V)$_{\rm XP}$ from the catalog of \citet{zhang2023}, which was derived using forward modeling of $Gaia$ XP spectra, were cross-validated with E(B$-$V)$_{\rm LAMOST}$, leading to the selection of $\sim$ 150 million high-reliability measurements. The combined dataset achieves a median precision of $\sim$ 0.03 mag for E(B$-$V). To model the reddening -- distance relationship along various lines-of-sight, we implemented a parametric approach that accounts for contributions from the local bubble, diffuse interstellar-medium, and multiple potential molecular clouds. The sky was adaptively partitioned based on stellar density, resulting in angular resolutions ranging from 3.4$^{\prime}$ to 58$^{\prime}$, with about half of the sky having a resolution better than 6.9$^{\prime}$. The reddening precision of our 3D map for individual stars reaches $\sim$ 0.01 mag in most regions at $|b| > 20^\circ$, but degrades to 0.01-0.05 mag at $|b| < 20^\circ$. The map reaches a maximum distance of 3-5 kpc in high-extinction regions with $|b| < 5^\circ$, and extends to 10-15 kpc elsewhere. An interactive platform and Python package have been developed for utilization of the 3D dust map. Available online: https://nadc.china-vo.org/data/dustmaps/.

astro-ph.GA↗

arXiv2025

A Comprehensive All-Sky Catalog of 3345 Molecular Clouds from Three-dimensional Dust Extinction

Understanding the distribution and properties of molecular clouds is crucial for tracing the structure and evolution of the interstellar medium and the large-scale morphology of the Milky Way. Here we present an all-sky catalog of 3,345 molecular clouds identified from our previous three-dimensional dust reddening map using a dendrogram-based clustering method with distance-adaptive parameters. The catalog spans heliocentric distances from 90 pc to 4.3 kpc and includes key physical properties for each cloud, including position, size, mass, surface density, and dust density. Approximately 650 clouds in our catalog are associated with the boundary of the Local Bubble, while around 740 clouds (excluding those associated with the Local Bubble) are located at high Galactic latitudes ($|b| > 20^\circ$). The spatial distribution of the cataloged clouds reveals prominent large-scale features in the Galactic disk, including coherent spur-like structures, large-scale cavities, and a more detailed view of the Local Bubble shell. These findings refine our understanding of how molecular clouds trace the Galactic spiral arm network and provide new insight into the spatial structure of the Local Bubble. The catalog serves as a valuable resource for future studies of star formation, Galactic structure, and the interaction between molecular clouds and large-scale ISM features.

astro-ph.GA↗

arXiv2025

The Dust Extinction Curve: Beyond R(V)

The dust extinction curve is typically parameterized by a single variable, R(V), in optical and near-infrared wavelengths. R(V) controls the slope of the extinction-vs.-wavelength curve, and is thought to reflect the grain-size distribution and composition of dust. Low-resolution, flux-calibrated BP/RP spectra from Gaia have allowed the determination of the extinction curve along sightlines to 130 million stars in the Milky Way and Magellanic Clouds. We show that these extinction curves contain more than a single degree of freedom - that is, that they are not simply described by R(V). We identify a number of components that are orthogonal to R(V) variation, and show that these components vary across the sky in coherent patterns that resemble interstellar medium structure. These components encode variation in the 770 nm extinction feature, intermediate-scale and very broad structure, and a newly identified feature at 850 nm, and likely trace both dust composition and local conditions in the interstellar medium. Correlations of the 770 nm and 850 nm features with R(V) suggest that their carriers become more abundant as the carrier of the 2175 Angstrom feature is destroyed. Our 24 million extinction-curve decompositions and feature equivalent-width measurements are publicly available at https://dx.doi.org/10.5281/zenodo.14005028.

astro-ph.GA↗

arXiv2025

MIKU-PAL: An Automated and Standardized Multi-Modal Method for Speech Paralinguistic and Affect Labeling

Acquiring large-scale emotional speech data with strong consistency remains a challenge for speech synthesis. This paper presents MIKU-PAL, a fully automated multimodal pipeline for extracting high-consistency emotional speech from unlabeled video data. Leveraging face detection and tracking algorithms, we developed an automatic emotion analysis system using a multimodal large language model (MLLM). Our results demonstrate that MIKU-PAL can achieve human-level accuracy (68.5% on MELD) and superior consistency (0.93 Fleiss kappa score) while being much cheaper and faster than human annotation. With the high-quality, flexible, and consistent annotation from MIKU-PAL, we can annotate fine-grained speech emotion categories of up to 26 types, validated by human annotators with 83% rationality ratings. Based on our proposed system, we further released a fine-grained emotional speech dataset MIKU-EmoBench(131.2 hours) as a new benchmark for emotional text-to-speech and visual voice cloning.

cs.SD↗

arXiv2025

Metallicities of 20 Million Giant Stars Based on Gaia XP spectra

We design an uncertainty-aware cost-sensitive neural network (UA-CSNet) to estimate metallicities from dereddened and corrected Gaia BP/RP (XP) spectra for giant stars. This method accounts for both stochastic errors in the input spectra and the imbalanced density distribution in [Fe/H] values. With a specialized architecture and training strategy, the UA-CSNet improves the precision of the predicted metallicities, especially for very metal-poor (VMP; $\rm [Fe/H] \leq -2.0$) stars. With the PASTEL catalog as the training sample, our model can estimate metallicities down to $\rm [Fe/H] \sim -4$. We compare our estimates with a number of external catalogs and conduct tests using star clusters, finding overall good agreement. We also confirm that our estimates for VMP stars are unaffected by carbon enhancement. Applying the UA-CSNet, we obtain reliable and precise metallicity estimates for approximately 20 million giant stars, including 360,000 VMP stars and 50,000 extremely metal-poor (EMP; $\rm [Fe/H] \leq -3.0$) stars. The resulting catalog is publicly available at https://doi.org/10.12149/101604. This work highlights the potential of low-resolution spectra for metallicity estimation and provides a valuable dataset for studying the formation and chemo-dynamical evolution of our Galaxy.

astro-ph.SR↗

arXiv2025

Massive Acquisition of Ultraviolet Color Excess Information from GALEX and UVOT Bands

This study employs stellar parameters from spectroscopic surveys and Zhang et al. based on Gaia XP spectra, along with photometric data from GALEX, UVOT, and Gaia, to obtain extensive ultraviolet color excess information for the relevant bands of GALEX and UVOT. By considering the impact of stellar parameters (\teff, \feh, and \logg) on intrinsic color indices, and utilizing the blue-edge method combined with a random forest algorithm, an empirical relationship between stellar parameters and intrinsic ultraviolet color indices is established. By combining observed color indices, the study derives color excesses for 11,624,802 and 65,531 stars in the GALEX/near-UV and far-UV bands, and 336,633, 137,739, and 253,271 stars in the UVOT/\uvwa, \uvmb, and \uvwb\ bands, constructing corresponding ultraviolet extinction maps. Notably, the color excess data for the GALEX/near-UV band shows a tenfold increase from previous results, with the extinction map covering approximately two-thirds of the sky at a resolution of 0.4$^{\circ}$. The typical uncertainties in the ultraviolet color excesses are 0.21 mag, 0.30 mag, 0.19 mag, 0.24 mag, and 0.21 mag for \enb, \efb, \ewab, \embb, and \ewbb, respectively. By comparing the spatial distributions of \rv\ derived from ultraviolet and Gaia optical band measurements with those obtained from infrared and optical data in previous works, it is evident that the \rv\ distributions based on the ultraviolet data show noticeable differences, with some regions even exhibiting opposite trends. This suggests that a single-parameter \rv\ extinction law may not be sufficient to simultaneously characterize the extinction behavior across infrared, optical, and ultraviolet bands.

astro-ph.GA↗

arXiv2025

Real-IAD D3: A Real-World 2D/Pseudo-3D/3D Dataset for Industrial Anomaly Detection

The increasing complexity of industrial anomaly detection (IAD) has positioned multimodal detection methods as a focal area of machine vision research. However, dedicated multimodal datasets specifically tailored for IAD remain limited. Pioneering datasets like MVTec 3D have laid essential groundwork in multimodal IAD by incorporating RGB+3D data, but still face challenges in bridging the gap with real industrial environments due to limitations in scale and resolution. To address these challenges, we introduce Real-IAD D3, a high-precision multimodal dataset that uniquely incorporates an additional pseudo3D modality generated through photometric stereo, alongside high-resolution RGB images and micrometer-level 3D point clouds. Real-IAD D3 features finer defects, diverse anomalies, and greater scale across 20 categories, providing a challenging benchmark for multimodal IAD Additionally, we introduce an effective approach that integrates RGB, point cloud, and pseudo-3D depth information to leverage the complementary strengths of each modality, enhancing detection performance. Our experiments highlight the importance of these modalities in boosting detection robustness and overall IAD performance. The dataset and code are publicly accessible for research purposes at https://realiad4ad.github.io/Real-IAD D3

cs.CV↗

arXiv2025

The Vertical Metallicity Gradient of the Galactic Disk for Mono-Age Stellar Populations in LAMOST

The vertical metallicity gradient of the Galactic disk offers valuable insights into the disk's formation and chemical evolution over time. We utilized the LAMOST-LRS young stellar sample to investigate this gradient and found that it approaches zero as stellar effective temperature (or age) increases (or decreases) across various Galactocentric distances. To validate this result, we analyzed 295 open clusters younger than 3 Gyr and 976 classical cepheids within the Galactic disk. The findings confirmed that, within a given narrow age range, the vertical metallicity gradient is effectively zero. This relationship between metallicity and age supports the ``upside-down'' disk formation theory, as it indicates that the youngest and most metal-rich stars dominate the midplane, while older and more metal-poor stars formed at larger vertical heights and currently tend to be at these heights. Overall, our results align well with theoretical predictions, offering further insight into the chemical evolution and structural properties of the Milky Way.

astro-ph.GA↗

arXiv2024

Fish-Speech: Leveraging Large Language Models for Advanced Multilingual Text-to-Speech Synthesis

Text-to-Speech (TTS) systems face ongoing challenges in processing complex linguistic features, handling polyphonic expressions, and producing natural-sounding multilingual speech - capabilities that are crucial for future AI applications. In this paper, we present Fish-Speech, a novel framework that implements a serial fast-slow Dual Autoregressive (Dual-AR) architecture to enhance the stability of Grouped Finite Scalar Vector Quantization (GFSQ) in sequence generation tasks. This architecture improves codebook processing efficiency while maintaining high-fidelity outputs, making it particularly effective for AI interactions and voice cloning. Fish-Speech leverages Large Language Models (LLMs) for linguistic feature extraction, eliminating the need for traditional grapheme-to-phoneme (G2P) conversion and thereby streamlining the synthesis pipeline and enhancing multilingual support. Additionally, we developed FF-GAN through GFSQ to achieve superior compression ratios and near 100\% codebook utilization. Our approach addresses key limitations of current TTS systems while providing a foundation for more sophisticated, context-aware speech synthesis. Experimental results show that Fish-Speech significantly outperforms baseline models in handling complex linguistic scenarios and voice cloning tasks, demonstrating its potential to advance TTS technology in AI applications. The implementation is open source at \href{https://github.com/fishaudio/fish-speech}{https://github.com/fishaudio/fish-speech}.

cs.SD↗

arXiv2024

An Empirical Extinction Curve Revealed by Gaia XP Spectra and LAMOST

We present a direct measurement of extinction curves using corrected $Gaia$ XP spectra of the common sources in $Gaia$ DR3 and LAMOST DR7. Our analysis of approximately 370 thousand high-quality samples yielded a high-precision average extinction curve for the Milky Way. After incorporating infrared photometric data from 2MASS and WISE, the extinction curve spans wavelengths from 0.336 to 4.6 $μ$m. We determine an average $R_{55}$ of $2.730 \pm 0.007$, corresponding to $R_V= 3.073 \pm 0.009$, and a near-infrared power-law index $α$ of $1.935 \pm 0.037$. Our study confirmed some intermediate-scale structures within the optical range. Two new features were identified at 540 and 769 nm, and their intensities exhibited a correlation with extinction and $R_V$. This extinction curve can be used to investigate the characteristics of dust and enhance the extinction correction of Milky Way stars. A Python package for this extinction curve is available.

astro-ph.GA↗

arXiv2024

A star-based method for precise flux calibration of the Chinese Space Station Telescope (CSST) slitless spectroscopic survey

The upcoming Chinese Space Station Telescope (CSST) slitless spectroscopic survey poses a challenge of flux calibration, which requires a large number of flux-standard stars. In this work, we design an uncertainty-aware residual attention network, the UaRA-net, to derive the CSST SEDs with a resolution of R = 200 over the wavelength range of 2500-10000 Åusing LAMOST normalized spectra with a resolution of R = 2000 over the wavelength range of 4000-7000 Å. With the special structure and training strategy, the proposed model can not only provide accurate predictions of SEDs but also their corresponding errors. The precision of the predicted SEDs depends on effective temperature (Teff), wavelength, and the LAMOST spectral signal-to-noise ratios (SNRs), particularly in the GU band. For stars with Teff = 6000 K, the typical SED precisions in the GU band are 4.2%, 2.1%, and 1.5% at SNR values of 20, 40, and 80, respectively. As Teff increases to 8000 K, the precision increases to 1.2%, 0.6%, and 0.5%, respectively. The precision is higher at redder wavelengths. In the GI band, the typical SED precisions for stars with Teff = 6000 K increase to 0.3%, 0.1%, and 0.1% at SNR values of 20, 40, and 80, respectively. We further verify our model using the empirical spectra of the MILES and find good performance. The proposed method will open up new possibilities for optimal utilization of slitless spectra of the CSST and other surveys.

astro-ph.IM↗

arXiv2024

A comprehensive correction of the Gaia DR3 XP spectra

By combining spectra from the CALSPEC and NGSL, as well as spectroscopic data from the LAMOST Data Release 7 (DR7), we have analyzed and corrected the systematic errors of the Gaia DR3 BP/RP (XP) spectra. The errors depend on the normalized spectral energy distribution (simplified by two independent ``colors'') and $G$ magnitude. Our corrections are applicable in the range of approximately $-0.5<BP-RP<2$, $3<G<17.5$ and $E(B-V)<0.8$. To validate our correction, we conduct independent tests by comparing with the MILES and LEMONY spectra. The results demonstrate that the systematic errors of $BP-RP$ and $G$ have been effectively corrected, especially in the near ultraviolet. The consistency between the corrected Gaia XP spectra and the MILES and LEMONY is better than 2 per cent in the wavelength range of $336-400$\,nm and 1 per cent in redder wavelengths. A global absolute calibration is also carried out by comparing the synthetic Gaia photometry from the corrected XP spectra with the corrected Gaia DR3 photometry. Our study opens up new possibilities for using XP spectra in many fields. A Python package is publicly available to do the corrections (https://doi.org/10.12149/101375 or https://github.com/HiromonGON/GaiaXPcorrection).

astro-ph.IM↗