检索结果-内蒙古大学图书馆

Simultaneous Speech Extraction for Multiple Target Speakers Under Meeting Scenarios

Journal of Shanghai Jiaotong University (science) 2024年 1-7页

作者： Zeng, Bang Suo, Hongbin Wan, Yulong Li, Ming School of Computer Science Wuhan University Wuhan430027 China Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems Duke Kunshan University Kunshan Jiangsu215316 China Data & amp AI Engineering System OPPO Beijing100125 China

The common target speech separation directly estimates the target source, ignoring the interrelationship between different speakers at each frame. We propose a multiple-target speech separation (MTSS) model to simultaneously extract each speaker’s voice from the mixed speech rather than just optimally estimating the target source. Moreover, we propose a speaker diarization (SD) aware MTSS system (SD-MTSS). By exploiting the target speaker voice activity detection (TSVAD) and the estimated mask, our SD-MTSS model can extract the speech signal of each speaker concurrently in a conversational recording without additional enrollment audio in advance. Experimental results show that our MTSS model achieves improvements of 1.38 dB signal-to-distortion ratio (SDR), 1.34 dB scale-invariant signal-to-distortion ratio (SISDR), and 0.13 perceptual evaluation of speech quality (PESQ) over the baseline on the WSJ0-2mix-extr dataset, separately. The SD-MTSS system makes a 19.2% relative speaker dependent character error rate reduction on the Alimeeting dataset. © Shanghai Jiao Tong University 2024.

关键词： Speech analysis

来源：评论

学校读者我要写书评

暂无评论

Control and Stability of Large-scale Power system with Highly Distributed Renewable Energy Generation:Viewpoints from Six Aspects

引用

CSEE Journal of Power and Energy systems 2023年第1期9卷 8-14页

作者： Qing-Hua Wu Anjan Bose Chanan Singh Joe H.Chow Gang Mu Yuanzhang Sun Zhaoxi Liu Zhigang Li Yang Liu School of Electric Power Engineering South China University of TechnologyGuangzhou 510640China School of Electrical Engineering&Computer Science Washington State UniversityPullmanWA 99164USA Department of Electrical and Computer Engineering Texas A&M UniversityCollege StationTX 77843USA Department of Electrical Computer and Systems EngineeringRensselaer Polytechnic Institute(RPI)TroyNYUSA Key Laboratory of Modern Power System Simulation and Control&Renewable Energy Technology Ministry of Education(Northeast Electric Power University)Jilin 132012China School of Electrical Engineering and Automation Wuhan UniversityWuhan 430072China

Power systems are moving toward a low-carbon or carbon-neutral future where high penetration of renewables is *** conventional fossil-fueled synchronous generators in the transmission network being replaced by renewable energy generation which is highly distributed across the entire grid,new challenges are emerging to the control and stability of large-scale power *** analysis and control methods are needed for power systems to cope with the ongoing *** the CSEE JPES forum,six leading experts were invited to deliver keynote speeches,and the participating researchers and professionals had extensive exchanges and discussions on the control and stability of power ***,potential changes and challenges of power systems with high penetration of renewable energy generation were introduced and explained,and advanced control methods were proposed and analyzed for the transient stability enhancement of power grids.

关键词： Distributed energy resources high converter penetration power system control renewable energy generation stability control transient stability

来源：评论

学校读者我要写书评

暂无评论

TESTING FACILITY LOCATION WITH CONSTRAINED QUEUE TIME PROBLEM: A CASE STUDY IN FLORIDA, USA

TESTING FACILITY LOCATION WITH CONSTRAINED QUEUE TIME PROBLE...

引用

2024 Winter Simulation Conference, WSC 2024

作者： Monteiro, Almir Antonio Schneider, Rafael de Almeida Guimarães, Vanessa González, Pedro Henrique System Engineering and Computer Science Program Federal University of Rio de Janeiro Brazil COPPEAD Graduate School of Business Federal University of Rio de Janeiro Brazil

ISBN: (纸本)9798331534202

This study addresses the Testing Facility Location with Constrained Queue Time Problem. This optimization problem focuses on determining the best places to deploy testing sites and their available testers for infectious diseases, while constraining the maximum time in the queue with a given probability. An integer programming model is introduced and applied to the three biggest counties, in terms of population, of Florida, United States. Moreover, the Monte Carlo method is used to evaluate the model’s output, aiming to check if the queueing time constraint is being satisfied. Through the experiments, a testing facility deployment plan can be determined for each county and further validated by the simulation. The results show that the solutions returned by the model behaved successfully when submitted to the Monte Carlo method, not exceeding the time in the queue in more than the predefined probability. © 2024 IEEE.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

Cross-modal change detection flood extraction based on self-supervised contrastive pre-training

Cross-modal change detection flood extraction based on self-...

引用

2024 ISPRS Technical Commission I Mid-term Symposium on Intelligent Sensing and Remote Sensing Application

作者： Feng, Wenqing Guan, Fangli Sun, Chenhao Xu, Wei School of Computer Science Hangzhou Dianzi University Hangzhou China Electrical & Information Engineering School Changsha University of Science & Technology Changsha China Information System and Management College National University of Defense Technology Changsha China

Flood extraction is a critical issue in remote sensing analysis. Accurate flood extraction faces challenges such as complex scenes, image differences across modalities, and a shortage of labeled samples. Traditional supervised deep learning algorithms demonstrate promising prospects in flood extraction. They mostly rely on abundant labeled data. However, in practical applications, there is a scarcity of available labeled samples for flood change regions, leading to an expensive acquisition of such data for flood extraction. In contrast, there is a wealth of unlabeled data in remote sensing images. Self-supervised contrastive learning (SSCL) provides a solution, allowing learning from unlabeled data without explicit labels. Inspired by SSCL, we utilized the open-source CAU-Flood dataset and developed a framework for cross-modal change detection in flood extraction (CMCDFE). We employed the Barlow Twin (BT) SSCL algorithm to learn effective visual feature representations of flood change regions from unlabeled cross-modal bi-temporal remote sensing data. Subsequently, these well-initialized weight parameters were transferred to the task of flood extraction, achieving optimal accuracy. We introduced the improved CS-DeepLabV3+ network for extracting flood change regions from cross-modal bi-temporal remote sensing data, incorporating the CBAM dual attention mechanism. By demonstrating on the CAU-Flood dataset, we proved that fine-tuning with only a pre-trained encoder can surpass widely used ImageNet pre-training methods without additional data. This approach effectively addresses downstream cross-modal change detection flood extraction tasks. © 2024 Wenqing Feng et al.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Research on Entity Recognition Method for Quality Standards of Concrete Prefabricated Components 1

Research on Entity Recognition Method for Quality Standards ...

引用

1st International Conference on Intelligent Manufacturing and Cloud Computing, ICIMCC 2024

作者： Zhang, Tingshu Tu, Ming Wang, Gefan Chen, Bingyong Zhao, Yishi Shang, Jianga School of Computer Science China University of Geosciences Wuhang China Intelligent Construction System Research Institute China Construction Third Engineering Buerau Group Co.L Wuhang China Engineering Research Center of Natural Resource Information Management and Digital Twin Engineering Software Ministry of Education School of Computer Science China University of Geosciences Wuhang China

ISBN: (纸本)9781643685779

In recent years, the country has released a large number of standard documents related to prefabricated concrete components. Due to the dispersion and complexity of these standards, it is difficult for industry managers to implement them. Therefore, it is imperative to establish a knowledge graph in the field of quality standards for precast concrete components to achieve knowledge management. The construction of knowledge graph first requires named entity recognition, but due to the specificity of the construction industry, entity recognition of the text in this field still suffers from the problems of low recognition accuracy and high resource consumption. Aiming at the low recognition accuracy and high resource consumption in named entity recognition due to the specificity of the industry, this paper proposes a named entity recognition model ALBERT-BiLSTM-SA-CRF for the field of precast concrete component quality standard, which can capture the full text and local feature information more effectively through the combination of BiLSTM and self-attention mechanism, and accurately recognize entities in the standard. Meanwhile, using ALBERT as the word embedding layer can play the role of reducing resource consumption and improving processing efficiency. © 2025 The Authors.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Positioning Control for Voice Coil Motor Using Unbalanced Multilevel Inverter Topology

Positioning Control for Voice Coil Motor Using Unbalanced Mu...

引用

2025 IEEE International Conference on Mechatronics, ICM 2025

作者： Takei, Gaku Obara, Hidemine Haneda, Ryo Nozaki, Takahiro Graduate School of Science and Technology Keio University Yokohama Japan Yokohama National University Department of Physics Electrical and Computer Engineering Yokohama Japan Keio University Department of System Design Engineering Yokohama Japan

ISBN: (纸本)9798331533892

This article proposes a new multi-level inverter (MLI) based on flying capacitor inverter (FCI), with focused on high-precision positioning control for a voice coil motor (VCM). Multi-level inverters (MLIs) have the characteristic that increasing the number of output voltage levels reduces the output voltage error. However, as the number of levels increases, the number of circuit elements increases, and the circuit becomes more complex. In addition, the output voltage amplitude for each level is constant in conventional inverters. As a result, such as high-precision positioning control of VCM, designing an appropriate inverter for a reference wave that contains a large amount of low-voltage components increases the number of circuit elements. Therefore, this paper proposes a MLI with two unbalanced dc-input voltages, referred to as unbalanced MLIs (UMLIs) hereinafter. This topology uses two different dc-input voltages, and it is possible to reduce the output voltage level in extremely low-voltage range compared to other voltage levels. Simulation results when the high-precision positioning control of the VCM confirm that the proposed UMLIs improves the control performance compared to the conventional FCIs with equal number of output voltage levels and uniform level widths. © 2025 IEEE.

关键词： motion control Multi-level inverter voice coil motor

来源：评论

学校读者我要写书评

暂无评论

λGrapher: A Resource-Efficient Serverless system for GNN Serving through Graph Sharing 24

λGrapher: A Resource-Efficient Serverless System for GNN Se...

引用

33rd ACM Web Conference, WWW 2024

作者： Hu, Haichuan Liu, Fangming Pei, Qiangyu Yuan, Yongjie Xu, Zichen Wang, Lin National Engineering Research Center for Big Data Technology and System The Services Computing Technology and System Lab Cluster and Grid Computing Lab in the School of Computer Science and Technology Huazhong University of Science and Technology 1037 Luoyu Road Wuhan China Peng Cheng Laboratory Huazhong University of Science and Technology China School of Mathematics and Computer Science Nanchang University China Paderborn University Paderborn Germany

ISBN: (纸本)9798400701719

Graph Neural Networks (GNNs) have been increasingly adopted for graph analysis in web applications such as social networks. Yet, efficient GNN serving remains a critical challenge due to high workload fluctuations and intricate GNN operations. Serverless computing, thanks to its flexibility and agility, offers on-demand serving of GNN inference requests. Alas, the request-centric serverless model is still too coarse-grained to avoid resource waste. Observing the significant data locality in computation graphs of requests, we propose λGrapher, a serverless system for GNN serving that achieves resource efficiency through graph sharing and fine-grained resource allocation. "Grapher features the following designs: (1) adaptive timeout for request buffering to balance resource efficiency and inference latency, (2) graph-centric scheduling to minimize computation and memory redundancy, and (3) resource-centric function management with fine-grained resource allocation catered to the resource sensitivities of GNN operations and function orchestration optimized to hide communication latency. We implement a prototype of λGrapher based on the representative open-source serverless platform Knative and evaluate it with real-world traces from various web applications. Our results show that λGrapher can achieve an average savings of 61.5% in memory resource and 47.2% in computing resource compared with the state of the arts while ensuring GNN inference latency. © 2024 ACM.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Towards Stricter Black-box Integrity Verification of Deep Neural Network Models 24

Towards Stricter Black-box Integrity Verification of Deep Ne...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： He, Chaoxiang Bai, Xiaofan Ma, Xiaojing Zhu, Bin B. Hu, Pingyi Fu, Jiayun Jin, Hai Zhang, Dongmei Huazhong University of Science and Technology Hubei Wuhan China Shanghai Jiao Tong University Shanghai China Microsoft Corporation Beijing China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security School of Cyber Science and Engineering Huazhong University of Science and Technology China 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

ISBN: (纸本)9798400706868

Cloud-based machine learning services offer significant advantages but also introduce the risk of tampering with cloud-deployed deep neural network (DNN) models. Black-box integrity verification (BIV) allows model owners and end-users to determine if a cloud-deployed DNN model has been tampered with by examining only the top-1 label responses. Fingerprinting generates fingerprint samples to query the model, achieving BIV with no impact on the model's accuracy. In this paper, we present BIVBench, the first comprehensive benchmark for BIV of DNN models. BIVBench covers 16 types of model modifications, providing extensive coverage of practical modification scenarios. Our analysis reveals that existing fingerprinting methods, which are typically focused on significant tampering, lack the sensitivity needed to effectively detect subtle yet common and potentially severe modifications. To address this limitation, we propose MiSentry (Model Integrity Sentry), a novel fingerprinting method that leverages meta-learning. MiSentry strategically incorporates a few subtly modified models into the meta-learning model zoo and maximizes the divergence of output predictions between the target model and the modified models in the model zoo to generate highly sensitive, generalizable, and effective fingerprint samples. Extensive evaluations using BIVBench demonstrate that MiSentry outperforms existing state-of-the-art methods overall and significantly surpasses them in detecting subtle modifications. The BIVBench and supplementary materials are available at: https://***/CGCL-codes/BIVBench. © 2024 ACM.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

ES-Mask: Evolutionary Strip Mask for Explaining Time Series Prediction 37

ES-Mask: Evolutionary Strip Mask for Explaining Time Series ...

引用

37th AAAI Conference on Artificial Intelligence, AAAI 2023

作者： Sun, Yifei Song, Cheng Lu, Feng Li, Wei Jin, Hai Zomaya, Albert Y. 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 Centre for Distributed and High Performance Computing School of Computer Science University of Sydney Australia

ISBN: (纸本)9781577358800

Machine learning models are increasingly used in time series prediction with promising results. The model explanation of time series prediction falls behind the model development and makes less sense to users in understanding model decisions. This paper proposes ES-Mask, a post-hoc and model-agnostic evolutionary strip mask-based saliency approach for time series applications. ES-Mask designs the mask consisting of strips with the same salient value in consecutive time steps to produce binary and sustained feature importance scores over time for easy understanding and interpretation of time series. ES-Mask uses an evolutionary algorithm to search for the optimal mask by manipulating strips in rounds, thus is agnostic to models by involving no internal model states in the search. The initial experiments on MIMIC-III data set show that ES-Mask outperforms state-of-the-art methods. Copyright © 2023, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Workload Prediction and Distribution in Cloud Computing using Deep Reinforcement Learning and LSTM

引用

Journal of Harbin Institute of Technology(New series) 2025年

作者： Nampally Vijay Kumar Satarupa Mohanty Prasant Kumar Pattnaik School of Computer Engineering KIIT Deemed to be University Department of Computer Science and Business System B V RAJU Institute of Technology

Maintaining high-quality service supply and sustainability in modern cloud computing is essential to ensuring optimal system performance and energy efficiency. A novel approach is introduced in this study to decrease a system.s overall delay and energy consumption by utilising a deep reinforcement learning(DRL)model to predict and allocate incoming workloads flexibly. The proposed methodology integrates workload prediction utilising long short-term memory(LSTM)networks with efficient load-balancing techniques led by deep Q-learning and Actor-Critic algorithms. By continuously analysing current and historical data,the model can efficiently allocate resources,prioritizing speed and energy preservation. The experimental findings demonstrate that our load balancing system,which utilises DRL,significantly reduces average response times and energy usage compared to traditional methods. This approach provides a scalable and adaptable strategy for enhancing cloud infrastructure performance. It consistently provides reliable and durable performance across a range of dynamic workloads.

关键词：

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：