检索结果-内蒙古大学图书馆

Improving Speaker Verification Back-End with Graph Neural Networks

Journal of Shanghai Jiaotong University (Science) 2025年 1-9页

作者： Chen, Jinfeng Fang, Zhihua He, Liang School of Computer Science and Technology Xinjiang University Urumqi830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China School of Intelligence Science and Technology Xinjiang University Urumqi830017 China Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

Currently, research on speaker verification tasks is primarily concentrated on enhancing deep speaker models to extract high-quality speaker embeddings. Nevertheless, this speaker embeddings can be regarded as potential graph structures. Therefore, this paper introduces a graph neural network-based speaker verification back-end approach, treating the speaker embeddings derived from the front-end as graph structures and leveraging graph neural networks to uncover the relationships among embeddings, thereby achieving superior-quality speaker embeddings. In addition, we propose a group updating method to solve the problem of memory overflow when the number of nodes is excessive. Extensive experiments and ablation studies were carried out on the VoxCeleb dataset, and the experimental outcomes validate the effectiveness of our proposed graph neural network speaker back-end in significantly boosting the performance of speaker verification systems. (Figure presented.) © Shanghai Jiao Tong University 2025.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

Dual-Path Spectrogram Refinement Network for Robust Speaker Verification

引用

Journal of Shanghai Jiaotong University (Science) 2025年 1-9页

作者： Wang, Zonghui Fang, Zhihua He, Liang School of Computer Science and Technology Xinjiang University Urumqi830017 China School of Intelligence Science and Technology Xinjiang University Urumqi830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

The accuracy and reliability of automatic speaker verification (ASV) face significant challenges in noisy environments. In recent years, joint training of speech enhancement front-end and ASV back-end has been widely applied to improve the robustness of ASV systems. Traditional joint training directly uses the enhanced speech features as the input of the back-end. However, the diversity of noise types and noise intensities will excessively suppress the enhanced features, resulting in speech distortion or residual noise. To alleviate this problem, we propose a dual-path spectrogram refinement network that enables the enhanced features to learn supplementary information from the separated noise features. In addition, we incorporate coordinate attention into the overall joint architecture to capture more comprehensive frequency and temporal information of the speaker from different spatial positions. We conduct extensive experiments on the VoxCeleb1 test set, the out-of-domain noise test set, and the VOiCES corpus. The experimental results demonstrate that our proposed method significantly improves the accuracy and robustness of speaker verification systems in both clean and noisy environments. (Figure presented.) © Shanghai Jiao Tong University 2025.

关键词： Spectrographs

来源：评论

学校读者我要写书评

暂无评论

Anomalous Sound Detection Using Time-Frequency Feature and Mixbatch

引用

Journal of Shanghai Jiaotong University (Science) 2025年 1-8页

作者： Huang, Shun Zhang, Yunxiang Fang, Zhihua Tang, Minrui Xu, Ruifeng He, Liang School of Computer Science and Technology Xinjiang University Urumqi830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China School of Intelligence Science and Technology Xinjiang University Urumqi830017 China Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

The sound emitted by machines under abnormal working conditions exhibits various frequency patterns. Currently, the most advanced anomalous sound detection (ASD) approach is to apply a multi-head self-attention mechanism to the Log-Mel spectrogram for automatic frequency pattern analysis. However, the Log-Mel spectrogram may filter out high-frequency components of abnormal sounds;thus the use of self-attention mechanisms on Log-Mel spectrogram seems to have certain limitations. In this paper, we construct a simple convolutional neural network to extract comprehensive frequency features from raw audio to complement spectral-temporal information fusion. The parameters of this neural network are continuously updated during the training process to extract better frequency features for downstream classification neural networks in ASD. Additionally, a method for data augmentation in the batch dimension was developed to help the classification model learn both types of comprehensive features simultaneously. The proposed method achieved an AUC of 94.13% and a pAUC of 89.09% on the DCASE 2020 Challenge Task 2 dataset. Even when using only the features proposed in this paper, an AUC of 84.62% was achieved. (Figure presented.). © Shanghai Jiao Tong University 2025.

关键词： Spectrographs

来源：评论

学校读者我要写书评

暂无评论

AccelES: Accelerating Top-K SpMV for Embedding Similarity via Low-bit Pruning 31

AccelES: Accelerating Top-K SpMV for Embedding Similarity vi...

引用

31st IEEE International Symposium on High Performance computer Architecture, HPCA 2025

作者： Zhai, Jiaqi Shi, Xuanhua Huang, Kaiyi Ye, Chencheng Hu, Weifang He, Bingsheng Jin, Hai Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Wuhan430074 China National University of Singapore School of Computing 119077 Singapore

ISBN: (纸本)9798331506476

In the realm of recommendation systems, achieving real-time performance in embedding similarity tasks is often hindered by the limitations of traditional Top-K sparse matrix-vector multiplication (SpMV) methods, which suffer from high latency due to inefficient memory access patterns. This paper identifies these critical gaps and introduces AccelES, a novel approach that significantly enhances the efficiency of Top-K SpMV. Our method employs a two-stage calculation scheme: the first stage utilizes a compact, low-bit dataset to quickly identify the most relevant entries, while the second stage performs full-precision calculations solely on this pruned subset, thereby minimizing computational overhead. Furthermore, AccelES incorporates innovative matrix representations, Ultra-CSR and Random-CSR, which optimize memory bandwidth utilization. Experimental results demonstrate that AccelES accelerates performance, surpassing state-of-the-art FPGA, GPU, and CPU solutions by factors of 3.4×, 2.5×, and 153.3×, respectively, under controlled conditions. These advancements not only enhance processing speed but also significantly improve real-time performance in recommendation systems, establishing AccelES as a pivotal contribution to the field of Top-K sparse matrix-vector multiplication. © 2025 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

VIPNet: Combining Viewpoint Information and Shape Priors for Instant Multi-view 3D Reconstruction 17th

VIPNet: Combining Viewpoint Information and Shape Priors fo...

引用

17th Asian Conference on computer Vision, ACCV 2024

作者： Ye, Weining Li, Zhixuan Jiang, Tingting School of Computer Science Peking University Beijing100871 China College of Computing and Data Science Nanyang Technological University Singapore Singapore National Engineering Research Center of Visual Technology National Key Laboratory for Multimedia Information Processing School of Computer Science National Biomedical Imaging Center Peking University Beijing100871 China

ISBN: (纸本)9789819609680

While the multi-view 3D reconstruction task has made significant progress, existing methods simply fuse multi-view image features without effectively leveraging available auxiliary information, especially the viewpoint information for guiding and associating features of different views. To this end, we propose to enhance multi-view 3D reconstruction with the power of viewpoint information. Specifically, a simple-yet-effective viewpoint estimator is designed to learn and provide comprehensive viewpoint knowledge for locating and associating learned features from different views. Moreover, to improve the 3D reconstruction quality when 2D images of only very few viewpoints are available, we propose to learn the shape prior knowledge to provide sufficient shape information for compensating the limited 2D observations. Overall, we present VIPNet, benefiting from Viewpoint Information and Shape Prior learning for high-quality multi-view 3D reconstruction. Extensive experiments validate the effectiveness of the proposed VIPNet, which achieves state-of-the-art performance on challenging datasets and shows well generalization ability in real-world scenarios. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

OHMiner: An Overlap-centric System for Efficient Hypergraph Pattern Mining 25

OHMiner: An Overlap-centric System for Efficient Hypergraph ...

引用

20th European Conference on computer Systems, EuroSys 2025, co-located 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS 2025

作者： Qi, Hao Luo, Kang He, Ligang Zhang, Yu Cai, Minzhi Dai, Jingxin He, Bingsheng Jin, Hai Zhang, Zhan Zhao, Jin Yue, Hengshan Yu, Hui Liao, Xiaofei National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Department of Computer Science University of Warwick United Kingdom National University of Singapore Singapore Zhejiang Lab China Jilin University China

ISBN: (纸本)9798400711961

Hypergraph Pattern Mining (HPM) aims to identify all the instances of user-interested subhypergraphs (patterns) in hypergraphs, which has been widely used in various applications. However, existing solutions either need significant enumeration overhead because they extend subhypergraphs at the granularity of vertices, or suffer from massive redundant computations because they often need to repeatedly fetch and process the same incident hyperedges for different vertices. This paper presents an overlap-centric system named OHMiner to efficiently support HPM. OHMiner proposes an overlap-centric execution model to determine the subhypergraphs isomorphism through computing and comparing overlaps among hyperedges using set operations. This model aims to efficiently handle the vertices that collectively share the same incident hyperedges. To automatically and precisely retrieve an arbitrary pattern’s overlapping semantics without performing redundant set computations, OHMiner further proposes a redundancy-free compiler, which constructs an Overlap Intersection Graph (OIG) for the pattern, optimizes the OIG, and generates an overlap-centric execution plan to guide the procedure of HPM. Moreover, OHMiner designs an overlap-centric parallel execution engine, which adopts an incremental overlap-pruned approach to fast validate candidates for HPM. Additionally, it proposes a degree-aware data store to support efficient generation of candidates. Through evaluating OHMiner on a broad range of real-world hypergraphs with various patterns, our experimental results show that OHMiner outperforms the state-of-the-art HPM system by 5.4×-22.2×. © 2025 Copyright held by the owner/author(s).

关键词： Compiler

来源：评论

学校读者我要写书评

暂无评论

InGaZnO4 and In2O3 Mobility Trend: The Role of Structural Disorder from Amorphous to Crystalline States

引用

ACS Materials Letters 2025年 2024-2030页

作者： Jang, Hyeongjun Kim, Taehyun Lee, Wonsok Cho, Minhee Ha, Daewon Alam, Muhammad A. Ye, Peide D. Jeong, Changwook Graduate School of Semiconductor Materials and Devices Engineering Ulsan National Institute of Science and Technology Ulsan44919 Korea Republic of Advanced Device Research Lab Semiconductor R&D Center Samsung Electronics Suwon16677 Korea Republic of School of Electrical and Computer Engineering Purdue University West LafayetteIN47907 United States

This study investigates the mobility trends of indium-gallium-zinc oxide (IGZO) thin-film transistors over a wide range of fabrication conditions, from amorphous to crystalline phases. By utilizing machine learning potential (MLP) to generate 70 distinct IGZO structures, we analyze electron mobility while taking into account structural disorder and electron scattering mechanisms. Our findings reveal that mobility peaks at the transition from amorphous to nanocrystalline phases, and then, as more ordered, crystalline structures emerge, the mobility decreases sharply due to the distortion of polyhedron of indium-oxygen in well-ordered regions. These results offer critical insights into optimizing the fabrication conditions for high-performance IGZO devices by identifying the ideal structural phase for achieving maximum mobility. © 2025 American Chemical Society.

关键词： Electron scattering

来源：评论

学校读者我要写书评

暂无评论

PUF-Based Authentication and Authorization Protocol for IoT 25th

PUF-Based Authentication and Authorization Protocol for Io...

引用

25th International Conference on Information Security Applications, WISA 2024

作者： Shih, Yu-Tse Huang, Shih-Ming Fan, Chun-I Department of Computer Science and Engineering National Sun Yat-sen University Kaohsiung804201 Taiwan Industrial Technology Research Institute Hsinchu310401 Taiwan Information Security Research Center National Sun Yat-sen University Kaohsiung804201 Taiwan Intelligent Electronic Commerce Research Center National Sun Yat-sen University Kaohsiung804201 Taiwan

ISBN: (纸本)9789819616237

With the rapid development of technology, smart devices have become indispensable tools for people, and IoT devices are ubiquitous, playing an important role in our daily lives. When using IoT device applications and services, users must go through complex authentication processes, which are time-consuming and pose various security issues. Not only must users be authenticated, but the devices must also be identified to ensure security. Physically Unclonable Functions (PUF) can be considered as hardware fingerprints due to their randomness and unpredictability, used to identify the uniqueness of devices. Given the limited computational power of IoT devices, the need for lightweight mechanisms is even more pronounced. Therefore, this protocol proposes a three-party mutual authentication using a smartphone involving the user, the server, and the IoT device. The PUF within the device generates a session key to authorize the IoT device to use and access the service. Finally, the contributions of this mechanism are highlighted through security analysis and comparison with related works. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

A Dual-Core Dual-Mode Class-F VCO With Wide Frequency Tuning Range Using Wide Inductance-Switching-Range Inductor

引用

IEEE Microwave and Wireless technology Letters 2025年第4期35卷 460-463页

作者： Hou, Yaru Li, Runlong Chi, Pei-Ling Yang, Tao University of electronic Science and Technology of China Chengdu610036 China Sichuan Province Engineering Research Center for Broadband Microwave Circuit High Density Integration Chengdu610036 China University of Electronic Science and Technology of China School of Electronic Science and Engineering Sichuan Chengdu610054 China National Yang Ming Chiao Tung University Department of Electrical and Computer Engineering Hsinchu300 Taiwan

A novel dual-core dual-mode class-F voltage-controlled oscillator (VCO) with wide frequency tuning range (TR) is proposed in this letter. It consists of two coupled parallel "8"-shaped inductor and two crossed-coupled VCO cores. To increase the TR of the proposed VCO without adding additional footprint size, a single-turn common-mode inductor is embedded inside the "8"-shaped inductor. By controlling the mode switches, the inductor can work in different modes with large inductance difference, realizing large VCO TR consequently. Then, the two coupled inductors were engineered to form the fundamental and third harmonic resonances, respectively, thereby producing a pseudo-square wave output waveform and realizing class-F operation. With the proposed configuration, the phase noise (PN) of the proposed VCO can be significantly reduced without increasing VCO core size. To demonstrate the proposed idea, a VCO prototype is fabricated in a 65-nm CMOS process with a core size of 1.235×0.8mm. It achieves a wide frequency TR from 2.84 to 7.04 GHz. The measured PN at 1-MHz offset is from -123.9 to -113.1 dBc/Hz, demonstrating an FOMT of 196.0-201.3 dBc/Hz. © 2023 IEEE.

关键词： Variable frequency oscillators

来源：评论

学校读者我要写书评

暂无评论

A Survey of Artificial Hummingbird Algorithm and Its Variants: Statistical Analysis, Performance Evaluation, and Structural Reviewing

引用

Archives of Computational Methods in engineering 2025年第1期32卷 269-310页

作者： Hosseinzadeh, Mehdi Rahmani, Amir Masoud Husari, Fatimatelbatoul Mahmoud Alsalami, Omar Mutab Marzougui, Mehrez Nguyen, Gia Nhu Lee, Sang-Woong Institute of Research and Development Duy Tan University Da Nang Viet Nam School of Medicine and Pharmacy Duy Tan University Da Nang Viet Nam Future Technology Research Center National Yunlin University of Science and Technology Yunlin Taiwan Department of Communication and Computer Engineering Faculty of Engineering Cihan University-Erbil Kurdistan Region Iraq Department of Electrical Engineering College of Engineering Taif University Taif21944 Saudi Arabia Department of Computer Engineering College of Computer Science King Khalid University Abha61413 Saudi Arabia School of Computer Science Duy Tan University Da Nang Viet Nam Pattern Recognition and Machine Learning Lab Gachon University 1342 Seongnamdaero Sujeonggu Seongnam13120 Korea Republic of

In the last few decades, metaheuristic algorithms that use the laws of nature have been used dramatically in numerous and complex optimization problems. The artificial hummingbird algorithm (AHA) is one of the metaheuristic algorithms that was invented in 2022 based on the foraging and migration behavior of the hummingbird for modeling and solving optimization problems. The algorithm initially starts with an initial random population of solutions. It then uses iterative processes and hummingbird position updates to balance exploration and exploitation toward the most optimal solutions. This paper has a detailed and extensive review of the AHA algorithm considering the aspects of hybrid, improved, binary, multi-objective, and optimization problems. In addition, a wide range of applications of AHA in various fields such as feature selection, image processing, scheduling, Internet of Things, classification, clustering, financial and economic issues, forecasting, wireless sensor networks, and many engineering challenges are explored. The statistical and numerical results showed that the AHA algorithm with deep learning methods, Levy flight, and opposition-based learning had the best performance. Also, the AHA algorithm is most widely used in solving multimodal optimization problems and continuous functions. © The Author(s) under exclusive licence to International center for Numerical Methods in engineering (CIMNE) 2024.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：