检索结果-内蒙古大学图书馆

10th Conference on Sound and Music Technology, CSMT 2023

作者： Gan, Xu Wu, Yifei Liu, Xinlu Duan, Ruilei Li, Wei School of Computer Science and Technology Fudan University Shanghai200438 China Department of Music Engineering ZheJiang Conservatory of Music Hangzhou310024 China Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai200433 China

ISBN: (纸本)9789819779611

The goal of the timbre transfer task is to apply the auditory characteristics of one instrument to another instrument. Past timbre transfer methods faced numerous challenges due to the limitations of the selected generation model. These challenges include difficulties in training, ambiguous results, poor diversity, and slow generation speed. To address these issues, we propose a diffusion model for timbre transfer, DiffTimb, which can be combined with vocoder to achieve single-note timbre transfer. Unlike traditional models that require training a specific model for each pair of timbre transfers, DiffTimb enables the conversion of various musical instrument timbres received in a single model, namely, many-to-many timbre transfer. We compare two Unet-based denoising frameworks and propose two feature fusion methods to fuse timbre and pitch features. We conduct unconditional and conditional generation pre-experiments to verify the generation ability of DiffTimb. To improve the generation effect, we clean the Nsynth dataset and get two subsets for our task. Experimental results show that DiffTimb has outperformed previous methods in both subjective and objective evaluations. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Audio acoustics

来源：评论

学校读者我要写书评

暂无评论

Communication-efficient and Decentralized Federated Minimax Optimization 60

Communication-efficient and Decentralized Federated Minimax ...

引用

60th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2024

作者： Ghiasvand, Sajjad Reisizadeh, Amirhossein Alizadeh, Mahnoosh Pedarsani, Ramtin University of California Department of Electrical and Computer Engineering Santa BarbaraCA93106 United States Massachusetts Institute of Technology Laboratory for Information and Decision Systems CambridgeMA02139 United States

ISBN: (纸本)9798331541033

As distributed learning applications like Federated Learning, the Internet of Things (IoT), and Edge Computing expand, addressing their limitations becomes crucial. We approach decentralized learning across a network of communicating clients or nodes, focusing on two primary challenges: data heterogeneity and adversarial robustness. To address these, we introduce a decentralized minimax optimization method incorporating two key components: local updates and gradient tracking. Minimax optimization serves as a fundamental tool for adversarial training, ensuring robustness. Local updates are vital in Federated Learning (FL) to alleviate the communication bottleneck, while gradient tracking is necessary to demonstrate convergence amid data heterogeneity. Our analysis of the proposed algorithm, Dec-Fed Track, in nonconvex-strongly-concave minimax optimization demonstrates its convergence to a stationary point. Additionally, numerical experiments support our theoretical results. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Efficient and accurate numerical-projection of electromagnetic multipoles for scattering objects

引用

Frontiers of Optoelectronics 2023年第4期16卷 215-226页

作者： Wenfei Guo Zizhe Cai Zhongfei Xiong Weijin Chen Yuntian Chen School of Optical and Electronic Information Huazhong University of Science and TechnologyWuhan 430074China Department of Electrical and Computer Engineering National University of SingaporeSingapore 117576Singapore Wuhan National Laboratory of Optoelectronics Huazhong University of Science and TechnologyWuhan 430074China Optics Valley Laboratory Wuhan 430074China

In this paper,we develop an efcient and accurate procedure of electromagnetic multipole decomposition by using the Lebedev and Gaussian quadrature methods to perform the numerical ***,we briefy review the principles of multipole decomposition,highlighting two numerical projection methods including surface and volume ***,we discuss the Lebedev and Gaussian quadrature methods,provide a detailed recipe to select the quadrature points and the corresponding weighting factor,and illustrate the integration accuracy and numerical efciency(that is,with very few sampling points)using a unit sphere surface and regular *** the demonstrations of an isotropic dielectric nanosphere,a symmetric scatterer,and an anisotropic nanosphere,we perform multipole decomposition and validate our numerical projection *** obtained results from our procedure are all consistent with those from Mie theory,symmetry constraints,and fnite element simulations.

关键词： Multipole decomposition Numerical quadrature Light scattering

来源：评论

学校读者我要写书评

暂无评论

Improving Speaker Verification Back-End with Graph Neural Networks

引用

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

Wireless Federated Learning Over Resource-Constrained Networks: Digital Versus Analog Transmissions

引用

IEEE Transactions on Wireless Communications 2024年第10期23卷 14020-14036页

作者： Yao, Jiacheng Xu, Wei Yang, Zhaohui You, Xiaohu Bennis, Mehdi Poor, H. Vincent Southeast University Nanjing210096 China Zhejiang Laboratory Hangzhou311121 China The College of Information Science and Electronic Engineering Zhejiang University Zhejiang Hangzhou310027 China The Center for Wireless Communications Oulu University Oulu90014 Finland The Department of Electrical and Computer Engineering Princeton University PrincetonNJ08544 United States

To enable wireless federated learning (FL) in communication resource-constrained networks, two communication schemes, i.e., digital and analog ones, are effective solutions. In this paper, we quantitatively compare these two techniques, highlighting their essential differences as well as respectively suitable scenarios. We first examine both digital and analog transmission schemes, together with a unified and fair comparison framework under imbalanced device sampling, strict latency targets, and transmit power constraints. A universal convergence analysis under various imperfections is established for evaluating the performance of FL over wireless networks. These analytical results reveal that the fundamental difference between the digital and analog communications lies in whether communication and computation are jointly designed or not. The digital scheme decouples the communication design from FL computing tasks, making it difficult to support uplink transmission from massive devices with limited bandwidth and hence the performance is mainly communication-limited. In contrast, the analog communication allows over-the-air computation (AirComp) and achieves better spectrum utilization. However, the computation-oriented analog transmission reduces power efficiency, and its performance is sensitive to computation errors from imperfect channel state information (CSI). Furthermore, device sampling for both schemes are optimized and differences in sampling optimization are analyzed. Numerical results verify the theoretical analysis and affirm the superior performance of the sampling optimization. © 2002-2012 IEEE.

关键词： Channel state information

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

Advancing Lymphoma Diagnosis in Histopathology Image Classification Using Multi Deep Learning Models

Iraqi Journal for Computer Science and Mathematics

引用

Iraqi Journal for computer Science and Mathematics 2025年第2期6卷 180-187页

作者： Elaraby, Ahmed Nechaevskiy, Andrey Saad, Aymen Department of Computer Science Faculty of Computers and Information South Valley University Qena83523 Egypt Cairo Egypt Meshcheryakov Laboratory of Information Technologies Joint Institute for Nuclear Research Joliot-Curie 6 Dubna141980 Russia Department of Information Technology Management Technical College Al-Furat Al-Awsat Technical University Kufa54003 Iraq School of Electrical Engineering Universiti Teknologi Malaysia Johor Skudai81310 UTM Malaysia

Deep learning’s rapid development is generating significant interest in its potential to improve medical imaging. It has shown promising results in detecting malignant lymphoma in histopathology medical images. Image classification methods are widely used to aid in making diagnoses from medical images. In recent years, deep learning methods have achieved high performance in detecting malignant lymphoma in histopathology images. This study proposes a novel approach to improving lymphoma diagnosis in histopathology images called the Lightweight Convolutional Neural Network (LWCNN). The proposed LWCNN model comprises multiple deep learning architectures, including a convolutional neural network (CNN) that has been trained to classify lymphoma subtypes based on histopathology images using ResNet50 and MobileNetV2. The LWCNN model aggregates the predictions of disparate architectures to arrive at a definitive diagnosis, leveraging the unique capabilities of each. A comprehensive dataset of annotated lymphoma histopathology images was assembled for the purpose of training the multi-deep learning model. To ensure a representative and diverse training set, the dataset was meticulously curated to encompass various subtypes of lymphoma. Performance evaluation of the proposed deep learning model for lymphoma classification using standard metrics revealed the following accuracies: LWCNN (97.34% training, 86.71% testing), ResNet50 (88.76% training, 86.37% testing), and MobileNetV2 (88.47% training, 86.60% testing). These results indicate that the LWCNN model significantly surpasses existing approaches in diagnostic accuracy. © 2025 The Author(s).

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

StackAMP: Stacking-Based Ensemble Classifier for Antimicrobial Peptide Identification

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第11期5卷 5666-5675页

作者： Karim, Tasmin Shaon, Md. Shazzad Hossain Ali, Md. Mamun Ahmed, Kawsar Bui, Francis M. Chen, Li Department of Computer Science and Engineering Birulia Dhaka Savar1216 Bangladesh University of Saskatchewan Division of Biomedical Engineering SaskatoonSKS7N 5A9 Canada University of Saskatchewan Department of Electrical and Computer Engineering SaskatoonSKS7N 5A9 Canada Health Informatics Research Laboratory Department of Computer Science and Engineering Birulia Dhaka Savar1216 Bangladesh Mawlana Bhashani Science and Technology University Group of Bio-photomati Information and Communication Technology Tangail Santosh1902 Bangladesh

Antimicrobial peptides (AMPs) play a vital role in the immune defence systems of various organisms and have garnered significant attention for their potential applications in biotechnology and medicine. There are several approaches to identifying AMPs including clinical isolation and characterization, functional genomics, microbiology techniques, and others. However, these methods are mostly expensive, time-consuming, and require well-equipped labs. To overcome these challenges, machine learning models are a potential solution due to their robustness and high predictive capability with less time and cost. In this study, we explored the efficacy of stacking-based ensemble machine-learning techniques to identify AMPs with higher accuracy and precision. Five distinct feature extraction methods, namely amino acid composition, dipeptide composition, moran autocorrelation, geary autocorrelation, and pseudoamino acid composition, were employed to represent the sequence characteristics of peptides. To build robust predictive models, different traditional machine learning algorithms were applied. Additionally, we developed a novel stacking classifier, aptly named StackAMP, to harness the collective power of these algorithms. Our results demonstrated the exceptional performance of the proposed StackAMP ensemble method in AMP identification, achieving an accuracy of 99.97%, 99.93% specificity, and 100% sensitivity. This high accuracy underscores the effectiveness of our approach, which has promising outcomes for the rapid and accurate identification of AMPs in various biological contexts. This study not only contributes to the growing body of knowledge in the field of AMP recognition but also offers a practical tool with potential applications in drug discovery, biotechnology, and disease prevention. © 2024 IEEE.

关键词： Amino acids

来源：评论

学校读者我要写书评

暂无评论

Zero-Phase Virtual Sampling-Based Anti-disturbance Repetitive Control for Permanent Magnet Synchronous Generators

引用

IEEE Transactions on Energy Conversion 2024年第2期40卷 950-958页

作者： Wei, Chun Song, Chenlong Zhang, Cheng Qiao, Wei Shen, Yangwu Zhejiang University of Technology College of Information Engineering Zhejiang Hangzhou310023 China University of Nebraska-Lincoln Power and Energy Systems Laboratory Department of Electrical and Computer Engineering LincolnNE68588-0511 United States China Three Gorges Corporation Wuhan Science and Technology Innovation Park Hubei Wuhan430010 China

This paper proposes an active disturbance rejection zero-phase virtual sampling repetitive control (ADR-ZVSRC) for permanent magnet synchronous generator (PMSG)-based wind energy conversion systems (WECSs) to mitigate the effects of uncertain disturbances and harmonic currents simultaneously. The active disturbance rejection control is designed to improve the anti-disturbance and robustness of the WECS and the zero-phase virtual sampling repetitive control (ZVSRC) is designed to eliminate the stator harmonic currents of the PMSG. The ZVSRC uses a zero-phase low-pass filter to overcome the drawbacks of phase shift in the traditional repetitive control and uses virtual sampling to make the controller adaptable to current frequency variations. The proposed ADR-ZVSRC strategy is tested on a 1500 W PMSG-based WECS emulator and the experimental results demonstrate that the proposed control strategy has superior current tracking, disturbance rejection, and harmonic suppression capabilities. © 1986-2012 IEEE.

关键词： Disturbance rejection

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

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：