湖南工程学院

Automatic Music Transcription (AMT) plays a critical role in converting music audio signals into editable and actionable symbolic scores, and holds significant practical applications in music domains such as music composition, digital music archiving, and automated music analysis. However, it still remain challenges to accurately identify notes, rhythms, and melodies, particularly in complex multi-track environments and dynamic note transcription tasks. Traditional AMT models typically rely on unimodal audio input, which struggles to effectively handle complex rhythmic structures and long-term dependencies between notes. To overcome these challenges, this paper proposes a novel AMT model based on a cross-modal Transformer architecture, named AMT-CMT. The model integrates audio features and structured score information by leveraging a dual-modality input mechanism and a cross-modal attention mechanism, to enable precise alignment between audio and score structures for high transcription performance especially in complex musical scenarios. The model incorporates a beat-depth-based note weighting mechanism that assigns hierarchical importance to notes according to their metrical positions, enhancing rhythmic structure modeling. It also employs a sparse Mixture-of-Experts (MoE) mechanism that dynamically routes inputs to specialized subnetworks, improving adaptability across diverse musical styles. Finally, we validate the superiority of our proposed AMT-CMT model by experiments on the MusicNet and URMP datasets with paired audio and MusicXML data. Experimental results indicate that the AMT-CMT model outperforms state-of-the-art models, with the improvement of 6.62% in Frame F1 and 6.63% in Onset F1. Furthermore, the model also improves the Onset+Offset F1 metric by 6.72% on the URMP and 6.67% on the MusicNet. These results fully demonstrates the robustness of our proposed model in complex musical scenarios for producing precise editable MusicXML files.

Developing low-cost, durable bifunctional electrocatalysts is essential for scalable rechargeable zinc-air batteries (ZABs). Though hierarchically porous MOF-derived carbon boosts oxygen reduction/evolution reaction (ORR/OER) kinetics, integrating abundant exposed sites, fast mass transport and stable conductive networks remains challenging. Herein, this study synthesize defect-rich hierarchical porous a-MnO2/Co@CNT-XM via CoZn-ZIF/CNT pyrolysis followed by mild KMnO4 etching. Pyrolytic Zn volatilization suppresses Co sintering and generates abundant Co-N-C sites; subsequent etching introduces carbon defects, oxygen groups and in-situ grown amorphous MnO2 (a-MnO2). Benefiting from synergy between Co-N-C, carbon defects and a-MnO2, optimized a-MnO2/Co@CNT-0.01M delivers outstanding bifunctional activity: ORR half-wave potential (0.84 V), onset potential (0.96 V), OER overpotential (393 mV@10 mA cm−2), 3.92 electron-transfer number for 4e− pathway, robust durability and methanol tolerance. The assembled ZAB attains 1.44 V open-circuit voltage, 119.1 mW cm−2 peak power density, 756.8 mAh·gZn‐1 specific capacity and ultra-long 280 h cycling stability. This work offers a universal strategy for high-performance non-noble-metal air cathode catalysts.

Interfacial solar-driven water evaporation offers a sustainable route to clean water production, but faces critical challenges of salt accumulation and organic contamination in complex industrial wastewater treatment. To address these challenges, we engineered a multifunctional 3D-printed hydrogel evaporator with vertically aligned grid architectures and hierarchical porosity. This unique structure promotes rapid water replenishment and Marangoni-driven salt back-diffusion through millimeter-scale channels, effectively preventing salt crystallization. By integrating carbon black and the metal-organic framework PCN-224 into the printing ink, we constructed a dual-functional photothermal-photocatalytic system. This synergistic combination not only enhances light absorption and photothermal conversion but also significantly reduces the water evaporation enthalpy. Coupled with heat-accelerated reaction kinetics, the system achieves efficient broad-spectrum photocatalytic degradation of organic pollutants. The resultant composite evaporator attains a high water evaporation rate of 2.04 kg m(-2) h(-1) under one-sun illumination, maintaining stable performance across a wide salinity range. Simultaneously, it degraded 96.5% of rhodamine B within 60 min under 1.5 kW m(-2) irradiation. This work demonstrates a synergistic strategy for simultaneous solar water production and purification, providing an efficient and environmentally friendly solution for advanced wastewater treatment.

As coal mining progresses to greater depths, the mechanical behavior and fracture mechanisms of composited roadway under complex hydrogeological conditions become critical for ensuring deep mining safety. This paper investigates the mechanical degradation and acoustic emission (AE) characteristics of coal–rock combined body under hydrochemical scouring-dissolution. Uniaxial compression tests combined with digital image correlation (DIC), nuclear magnetic resonance (NMR), scanning electron microscopy (SEM), energy-dispersive spectroscopy (EDS), and X-ray diffraction (XRD) characterize the distinct fracture mechanics and microstructural responses of coal–sandstone combined body to varying pH levels and flow rates. Key findings include: (1) Under more acidic solutions and higher flow rates, coal exhibits a transition from brittle to ductile failure, characterized by microcrack propagation and localized deformation, while sandstone undergoes significant fracture network development due to mineral dissolution and cementation degradation. (2) AE analysis demonstrates coal exhibits uniform microcrack propagation through dense low-energy emissions and stable b-values driven by flow forces, whereas sandstone displays localized high-energy AE bursts with unstable b-values during acid-induced macrofracture development. (3) Microstructural analysis highlights that sandstone is more sensitive to pH-induced dissolution, with rapid pore-fracture expansion, while coal exhibits greater susceptibility to flow rate-driven scouring, causing interlayer delamination and surface erosion. These findings underscore the critical role of groundwater chemistry in shaping the mechanical behavior of coal–rock systems, providing a foundation for safer and more efficient deep mining practices.

Signs of water flow erosion are evident in the bedrock of underground engineering, particularly in regions with abundant groundwater, where the mechanical properties of the bedrock are significantly compromised. Investigating the impact of water flow rate on these properties is crucial. This study examines four flow rates (v = 0, 0.1, 0.3, and 0.5 m/s). Sandstone specimens were subjected to scouring for 49 days, followed by uniaxial compression tests, with real-time monitoring via an acoustic emission system. Additionally, the study employed scanning electron microscopy (SEM) and x-ray diffractometry (XRD) to analyze the changes in the rock's microscopic structure under varying solution flow rates, as well as the alterations in compressive strength, deformation, and mechanical parameters. The results indicate that: (1) Increasing solution flow rate reduces the uniaxial compressive strength of sandstone: compared with the dry sample, the strength of the specimen exposed to a flow rate of 0.5 m/s decreases by 45.05