检索结果-内蒙古大学图书馆

2019 4th International Conference on intelligent computing and signal processing, ICSP 2019

作者： Zhou, Jian Hu, Yuting Lian, Hailun Pang, Cong Wang, Huabin Tao, Liang Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei AnHui230039 China School of Computer Science and Technology Anhui University Hefei AnHui230601 China

Converting whisper to normal vocalized speech has been a hot research topic in speech signal processing area. A complete and large scale whisper database is a major basis for this task. In this paper, we propose a multimodal whisper database in Chinese mandarin. A total of 103 syllables and 100 sentences were carefully selected. 5 male and 5 female participants pronounced the syllables and sentences in whisper and normal styles respectively, result in 4096 parallel speech utterances and 263, 849 frames of voicing face and lip image sequences. The beginning and ending sample point of each syllable were labeled both for speech signal and voicing face video. The lip region of interest were also extracted and provided in the proposed database. Experiments in various speech conversion tasks in different speech database show the effectiveness of the proposed multimodal whisper speech database. © 2019 IOP Publishing Ltd. All rights reserved.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Remote Sensing Image Registration via Modality Perception and Self-Supervised Position Estimation

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Xiao, Yun Zhang, Chunlei Jiang, Bo Chen, Yuan Tang, Jin Anhui University Key Laboratory of Intelligent Computing & Signal Processing (Anhui University) Anhui Provincial Key Laboratory of Security Artificial Intelligence School of Artificial Intelligence Hefei 230601 China Anhui University Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Hefei 230601 China Anhui University School of Internet Hefei 230601 China

Multi-modal remote sensing images registration ensures that images from different sensors or modalities are spatial and informational consistent for effective comparison and analysis. However, due to the non-linear modality gaps that exist between images, making it difficult to focus only on the spatial position differences of the images and ignore the modality gaps. In this paper, to address this issue, we propose a new framework for Multi-Modal remote sensing image Registration, named MMRNet. The proposed framework comprises the following main aspects. First, a novel self-supervised Positional Misalignment Estimator (PME) is designed for multi-modal image registration. PME is able to efficiently overcome the modality gaps and learn the positional differences between multi-modal images more reliably, optimizing the registration loss by minimizing the positional differences directly. Then, a new paradigm of modality translation, termed Modality Perception Module (MPM), is introduced to effectively learn modality gaps and perform modality translation in the case of positional misalignment. Finally, we further design the modality perception guidance loss to supervise the modality translation task, which can encourage the fidelity of the generated pseudo-modality images. Our registration network integrates both rigid registration model and non-rigid registration model. Experimental results demonstrate that the proposed registration framework can obtain obviously superior performance in both rigid and non-rigid image registration tasks on optical-SAR data, optical-map data and optical-infrared data. © 1980-2012 IEEE.

关键词： image registration modality translation Multi-modal learning remote sensing processing rigid and non-rigid transformation

来源：评论

学校读者我要写书评

暂无评论

A Pilot Allocation Method of Jointing Cell Grouping and Alliance Game in Massive MIMO System

A Pilot Allocation Method of Jointing Cell Grouping and Alli...

引用

第二届材料科学应用与能源材料国际研讨会

作者： Feiyue Wang Hui Zhi Ziju Huang Key Lab of Computing Intelligent and Signal Processing(Ministry of Education) Anhui University

In order to improve the uplink channel estimation performance and reduce pilot contamination(PC),this paper proposes a pilot allocation method of jointing cell grouping and alliance game(JCG-AG) for massive multiple-input multiple-output(MIMO) cellular *** can be divided into two ***,by properly dividing all cells into different cell-groups,the users in different cell-groups are allocated different orthogonal pilot ***,the users in the same cell-group are further divided into several mutually disjoint *** belonging to different sub-alliances are allocated different pilots,and users belonging to the same sub-alliance reuse the same *** the second step,the alliance formation algorithm is used to suppress *** JCG-AG method takes practical application as the starting point,focuses on the random distribution of users,and uses the idea of alliance *** these make it more flexible and *** demonstrated in the simulation results,the JCG-AG method can greatly mitigate the PC and reduce the average mean square error(MSE) for all channel estimations in the uplink.

关键词： MSE red A Pilot Allocation Method of Jointing Cell Grouping and Alliance Game in Massive MIMO System

来源：评论

学校读者我要写书评

暂无评论

A New User Grouping and Power Allocation Scheme for Downlink Non-orthogonal Multiple Access Systems

A New User Grouping and Power Allocation Scheme for Downlink...

引用

2019 3rd International Conference on Data Mining, Communications and Information Technology (DMCIT 2019)

作者： Yin Wang Xiaohui Li Wenwu Wang Gongquan Zhang Hongwei Zhang Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University

In this paper,we propose a new user grouping and power allocation scheme based on beamforming for downlink non-orthogonal multiple access *** proposed user grouping scheme can effectively reduce the interference from the other user and other beams as well,and can effectively improve the weak user rate especially when the SNR is not *** addition,a power allocation scheme that can maximize the sum capacity while satisfying a certain fairness index is *** the simulation results,the user grouping and power allocation method proposed in this paper can not only improve the overall system throughput performance,but also improve the fairness of weak users.

关键词： SNR A New User Grouping and Power Allocation Scheme for Downlink Non-orthogonal Multiple Access Systems

来源：评论

学校读者我要写书评

暂无评论

Differentiable neural architecture learning for efficient neural network design

arXiv

引用

arXiv 2021年

作者： Guo, Qingbei Wu, Xiao-Jun Kittler, Josef Feng, Zhiquan Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi214122 China Shandong Provincial Key Laboratory of Network based Intelligent Computing University of Jinan Jinan250022 China Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

Automated neural network design has received ever-increasing attention with the evolution of deep convolutional neural networks (CNNs), especially involving their deployment on embedded and mobile platforms. One of the biggest problems that neural architecture search (NAS) confronts is that a large number of candidate neural architectures are required to train, using, for instance, reinforcement learning and evolutionary optimisation algorithms, at a vast computation cost. Even recent differentiable neural architecture search (DNAS) samples a small number of candidate neural architectures based on the probability distribution of learned architecture parameters to select the final neural architecture. To address this computational complexity issue, we introduce a novel architecture parameterisation based on scaled sigmoid function, and propose a general Differentiable Neural Architecture Learning (DNAL) method to optimize the neural architecture without the need to evaluate candidate neural networks. Specifically, for stochastic supernets as well as conventional CNNs, we build a new channel-wise module layer with the architecture components controlled by a scaled sigmoid function. We train these neural network models from scratch. The network optimization is decoupled into the weight optimization and the architecture optimization, which avoids the interaction between the two types of parameters and alleviates the vanishing gradient problem. We address the non-convex optimization problem of neural architecture by the continuous scaled sigmoid method with convergence guarantees. Extensive experiments demonstrate our DNAL method delivers superior performance in terms of neural architecture search cost, and adapts to conventional CNNs (e.g., VGG16 and ResNet50), lightweight CNNs (e.g., MobileNetV2) and stochastic supernets (e.g., ProxylessNAS). The optimal networks learned by DNAL surpass those produced by the state-of-the-art methods on the benchmark CIFAR-10 and ImageN

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-channel Compressed Sensing Optimization Based on Singular Value Decomposition

Multi-channel Compressed Sensing Optimization Based on Singu...

引用

2019第十一届数字图像处理国际会议

作者： Cheng Zhang Yuanyuan Zhu Jun Tang Qianwen Chen Meiqin Wang Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University

Distributed compressed sensing theory is applied to many practical problems,ECG signal,color imaging,*** order to improve the reconstruction accuracy of multi-dimensional signals,this paper applies singular value decomposition to the multi-measure vector problem in DCS,then distributed compressed sensing reconstruction method based on singular value decomposition is *** method can achieve row orthogonality of the measurement matrix and does not affect the design of the reconstruction *** experiments verify the effectiveness of the proposed method,which can significantly improve the reconstruction quality of the signal and the robustness to noise.

关键词： Distributed compressed sensing (DCS) Multiple measurement vector problem(MMV) singular value decomposition(SVD) Separable Design

来源：评论

学校读者我要写书评

暂无评论

The Downlink Performance of Massive MIMO Systems under Different Uplink Pilot Allocation Schemes

The Downlink Performance of Massive MIMO Systems under Diffe...

引用

第二届材料科学应用与能源材料国际研讨会

作者： Ziju Huang Hui Zhi Feiyue Wang Key Lab of Computing Intelligent and Signal Processing(Ministry of Education) Anhui University

In the scenario of time division duplexing(TDD) massive multiple-input multiple-output(MIMO) system,when there is pilot contamination(PC) in the uplink,different pilot allocation schemes will affect the results of the uplink channel *** the channel estimation results are used for downlink transmission precoding,which will further affects the downlink *** paper analyses the impact of different pilot allocation(PA) schemes on downlink *** theoretical analysis,the system downlink signal to interference plus noise ratio(SINR) and spectral efficiency expressions of different pilot allocation schemes are obtained *** simulation results show that the pilot allocation schemes with cell grouping is better than the schemes without cell *** SINR increases as the number of cell grouping increases,and the spectrum efficiency increases first and then decreases as the number of cell grouping increases.

关键词： TDD The Downlink Performance of Massive MIMO Systems under Different Uplink Pilot Allocation Schemes

来源：评论

学校读者我要写书评

暂无评论

A BVP signal Detection Method of Anti-Motion Interference

A BVP Signal Detection Method of Anti-Motion Interference

引用

International Congress on Image and signal processing, BioMedical Engineering and Informatics

作者： Qing Wan Xiaopei Wu Chao Zhang Anhui University Intelligent Computing and Signal Processing Key Lab Hefei China

The noncontact detection methods of blood volume pulse (BVP) based on facial videos have become a hot spot in recent years. However, these kinds of methods are highly sensitive to face movement. To address this problem, a novel BVP detection method based on kanade-lucas-tomasi (KLT) and independent component analysis (ICA) was proposed, in which, KLT method was employed for tracking and locating the region of interest (ROI) in facial images, and ICA method was used to improve the signal to noise ratio (SNR) of BVP signal. Based on 120 recorded facial videos, we carried out the comparative study of the proposed method and other commonly-used methods, the experimental results show that our method has obvious advantages in eliminating motion interference. In the implementation of the blind source separation method, we also conducted four separation methods. The results show that the second order blind identification (SOBI) algorithm is the best one to separate the BVP signal.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multilevel Characteristic Basis Function Method with ACA for Accelerated Solution of Electrically Large Scattering Problems

引用

Transactions of Nanjing University of Aeronautics and Astronautics 2018年第3期35卷 449-454页

作者： Li Chenlu Sun Yufa Wang Zhonggen Wang Guohua Key Laboratory of Intelligent Computing & Signal Processing Ministry of EducationAnhui University College of Electrical and Information Engineering Anhui University of Science and Technology

The multilevel characteristic basis function method(MLCBFM)with the adaptive cross approximation(ACA)algorithm for accelerated solution of electrically large scattering problems is studied in this *** the conventional MLCBFM based on Foldy-Lax multiple scattering equations,the improvement is only made in the generation of characteristic basis functions(CBFs).However,it does not provide a change in impedance matrix filling and reducing matrix calculation procedure,which is *** reality,all the impedance and reduced matrix of each level of the MLCBFM have low-rank property and can be calculated ***,ACA is used for the efficient generation of two-level CBFs and the fast calculation of reduced matrix in this *** results are given to demonstrate the accuracy and efficiency of the method.

关键词： multilevel characteristic basis function method(MLCBFM) adaptive cross approximation(ACA) characteristic basis functions(CBFs) electromagnetic scattering

来源：评论

学校读者我要写书评

暂无评论

An End to End Method of Whisper Enhancement

An End to End Method of Whisper Enhancement

引用

IEEE International Conference on Information Communication and signal processing (ICICSP)

作者： Yan Huang HaiLun Lian Jian Zhou HuaBin Wang Liang Tao MOE Key Laboratory of Intelligent Computing and Signal Processing Anhui University Hefei China

In this paper, we propose a method of enhancing whisper, using whisper without any pretreatment combined with Wavenet. Our method is end-to-end, that is, inputing noised whisper to get clean whisper. The input to our method is the original whisper without any processing, reducing the loss of features caused by other operations. We use speech denoising Wavenet to enhance whisper. Wavenet can not only enhance whisper well, but also tackle the issue of intelligibility. Specifically, use symmetric dilated convolution to obtain noisy speech context, help the model to enhance the speech for better denoising effect. Experimental results show that the enchanced whisper gains better performance both in the aspect of speech quality and intelligibility.

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：