检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial intelligence 2023年第2期4卷 268-281页

作者： Tian, Ye Pan, Jingwen Yang, Shangshang Zhang, Xingyi He, Shuping Jin, Yaochu Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information Technology Hefei230601 China Hefei Comprehensive National Science Center Institute of Artificial Intelligence Hefei230088 China Anhui University School of Computer Science and Technology Hefei230601 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Artificial Intelligence Hefei230601 China Anhui University Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment School of Electrical Engineering and Automation Hefei230601 China Bielefeld University Faculty of Technology Bielefeld33619 Germany

The sparse adversarial attack has attracted increasing attention due to the merit of a low attack cost via changing a small number of pixels. However, the generated adversarial examples are easily detected in vision since the perturbation to each pixel is relatively large. To achieve imperceptible and sparse adversarial attacks, this article formulates a bi-objective constrained optimization problem, simultaneously minimizing the 0 and 2 distances to the original image, and proposes a dual-population-based constrained evolutionary algorithm to solve it. The proposed method solves the optimization problem by evolving two populations, where one population is responsible for finding feasible solutions (i.e., successful attacks) and the other one is to minimize both the 0 and 2 distances. Moreover, a population initialization strategy and two genetic operators are customized to accelerate the convergence speed. Experimental results indicate that the proposed method can achieve high success rates with low attack costs, and strikes a better balance between the 0 and 2 distances than state-of-the-art methods. © 2020 IEEE.

关键词： Evolutionary algorithms

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

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

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

A Fast Clustering Based Evolutionary Algorithm for Super-Large-Scale Sparse Multi-Objective Optimization

引用

IEEE/CAA Journal of Automatica Sinica 2023年第4期10卷 1048-1063页

作者： Ye Tian Yuandong Feng Xingyi Zhang Changyin Sun Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information TechnologyAnhui UniversityHefei 230601China School of Computer Science and Technology Anhui UniversityHefei 230601China School of Artificial Intelligence Anhui UniversityHefei 230601China School of Automation Southeast UniversityNanjing 210096China

During the last three decades,evolutionary algorithms(EAs)have shown superiority in solving complex optimization problems,especially those with multiple objectives and non-differentiable ***,due to the stochastic search strategies,the performance of most EAs deteriorates drastically when handling a large number of decision *** tackle the curse of dimensionality,this work proposes an efficient EA for solving super-large-scale multi-objective optimization problems with sparse optimal *** proposed algorithm estimates the sparse distribution of optimal solutions by optimizing a binary vector for each solution,and provides a fast clustering method to highly reduce the dimensionality of the search *** importantly,all the operations related to the decision variables only contain several matrix calculations,which can be directly accelerated by *** existing EAs are capable of handling fewer than 10000 real variables,the proposed algorithm is verified to be effective in handling 1000000 real ***,since the proposed algorithm handles the large number of variables via accelerated matrix calculations,its runtime can be reduced to less than 10%of the runtime of existing EAs.

关键词： Evolutionary computation fast clustering sparse multi-objective optimization super-large-scale optimization

来源：评论

学校读者我要写书评

暂无评论

Alignment-Free RGB-T Salient Object Detection: A Large-scale Dataset and Progressive Correlation Network

arXiv

引用

arXiv 2024年

作者： Wang, Kunpeng Chen, Keke Li, Chenglong Tu, Zhengzheng Luo, Bin Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University China Anhui Provincial Key Laboratory of Security Artificial Intelligence School of Artificial Intelligence Anhui University China

Alignment-free RGB-Thermal (RGB-T) salient object detection (SOD) aims to achieve robust performance in complex scenes by directly leveraging the complementary information from unaligned visible-thermal image pairs, without requiring manual alignment. However, the labor-intensive process of collecting and annotating image pairs limits the scale of existing benchmarks, hindering the advancement of alignment-free RGB-T SOD. In this paper, we construct a large-scale and high-diversity unaligned RGB-T SOD dataset named UVT20K, comprising 20,000 image pairs, 407 scenes, and 1256 object categories. All samples are collected from real-world scenarios with various challenges, such as low illumination, image clutter, complex salient objects, and so on. To support the exploration for further research, each sample in UVT20K is annotated with a comprehensive set of ground truths, including saliency masks, scribbles, boundaries, and challenge attributes. In addition, we propose a Progressive Correlation Network (PCNet), which models inter- and intra-modal correlations on the basis of explicit alignment to achieve accurate predictions in unaligned image pairs. Extensive experiments conducted on unaligned and aligned datasets demonstrate the effectiveness of our method. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Gradient-Guided Evolutionary Approach to Training Deep Neural Networks

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2022年第9期33卷 4861-4875页

作者： Yang, Shangshang Tian, Ye He, Cheng Zhang, Xingyi Tan, Kay Chen Jin, Yaochu Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information Technology Anhui University Hefei China Department of Computer Science and Engineering Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Southern University of Science and Technology Shenzhen China Department of Computing The Hong Kong Polytechnic University Hong Kong SAR Department of Computer Science University of Surrey Guildford U.K

It has been widely recognized that the efficient training of neural networks (NNs) is crucial to classification performance. While a series of gradient-based approaches have been extensively developed, they are criticized for the ease of trapping into local optima and sensitivity to hyperparameters. Due to the high robustness and wide applicability, evolutionary algorithms (EAs) have been regarded as a promising alternative for training NNs in recent years. However, EAs suffer from the curse of dimensionality and are inefficient in training deep NNs (DNNs). By inheriting the advantages of both the gradient-based approaches and EAs, this article proposes a gradient-guided evolutionary approach to train DNNs. The proposed approach suggests a novel genetic operator to optimize the weights in the search space, where the search direction is determined by the gradient of weights. Moreover, the network sparsity is considered in the proposed approach, which highly reduces the network complexity and alleviates overfitting. Experimental results on single-layer NNs, deep-layer NNs, recurrent NNs, and convolutional NNs (CNNs) demonstrate the effectiveness of the proposed approach. In short, this work not only introduces a novel approach for training DNNs but also enhances the performance of EAs in solving large-scale optimization problems.

关键词： Artificial neural networks Training Optimization Search problems Scalability Complexity theory Genetic algorithms Deep neural networks (DNNs) evolutionary algorithm (EA) genetic operator gradient descent sparsity

来源：评论

学校读者我要写书评

暂无评论

Spatially Informed Independent vector analysis for Source Extraction based on the convolutive Transfer Function Model 48

Spatially Informed Independent vector analysis for Source Ex...

引用

48th IEEE International Conference on Acoustics, Speech and signal processing, ICASSP 2023

作者： Wang, Xianrui Brendel, Andreas Huang, Gongping Yang, Yichen Kellermann, Walter Chen, Jingdong Northwestern Polytechnical University CIAIC and Shaanxi Provincial Key Laboratory of Artificial Intelligence Xi'an710072 China Friedrich-Alexander-Universität Multimedia Communications and Signal Processing Erlangen-Nürnberg Germany

ISBN: (纸本)9781728163277

Spatial information can help improve source separation performance. Numerous spatially informed source extraction methods based on the independent vector analysis (IVA) have been developed, which can achieve reasonably good performance in non- or weakly reverberant environments. However, the performance of those methods degrades quickly as the reverberation increases. The underlying reason is that those methods are derived based on the multiplicative transfer function model with a rank-1 assumption, which does not hold true if reverberation is strong. To circumvent this issue, this paper proposes to use the convolutive transfer function (CTF) model to improve the source extraction performance and develop a spatially informed IVA algorithm. Simulations demonstrate the efficacy of the developed method even in highly reverberant environments. © 2023 IEEE.

关键词： Transfer functions

来源：评论

学校读者我要写书评

暂无评论

An airborne radar clutter suppression algorithm based on negative log-likelihood minimization

引用

IEEE Sensors Journal 2025年第12期25卷 22430-22440页

作者： Cao, Junxiang Wang, Tong Cui, Weichen National Key Laboratory of Radar Signal Processing Xidian University Xi’an China Beijing Aerospace Automatic Control Institute Beijing China National Key Laboratory of Science and Technology on Aerospace Intelligence Control Beijing China

Space time adaptive processing (STAP) plays an important role in the field of airborne radar clutter suppression. However, due to the inhomogeneity of the clutter environment, the radar system is unable to obtain enough training samples, which will lead to a significant reduction in the clutter suppression performance of STAP. To address this issue, an airborne radar clutter suppression algorithm based on negative log-likelihood minimization is proposed in this work. Firstly, we use the negative log-likelihood function minimization criterion to give the cost function for estimating the clutter plus noise covariance matrix (CNCM), which is a nonconvex optimization problem. Secondly, to estimate the CNCM, we use the majorization-minimization(MM) algorithm and alternating optimization to iteratively solve the above nonconvex problem. Finally, we utilize the estimated CNCM to construct a space time filter to suppress the ground clutter. Simulation results show that the proposed algorithm performs well in terms of both clutter suppression and convergence speed in the case of insufficient training samples. © 2001-2012 IEEE.

关键词： Radar clutter

来源：评论

学校读者我要写书评

暂无评论

An Improved Optimal Transport Kernel Embedding Method with Gating Mechanism for Singing Voice Separation and Speaker Identification 48

An Improved Optimal Transport Kernel Embedding Method with G...

引用

48th IEEE International Conference on Acoustics, Speech and signal processing, ICASSP 2023

作者： Yuan, Weitao Bian, Yuren Wang, Shengbei Unoki, Masashi Wang, Wenwu Tiangong University Tianjin Key Laboratory of Autonomous Intelligence Technology and Systems China Japan Advanced Institute of Science and Technology Japan University of Surrey Centre for Vision Speech and Signal Processing Guildford United Kingdom

ISBN: (纸本)9781728163277

Singing voice separation (SVS) and speaker identification (SI) are two classic problems in speech signal processing. Deep neural networks (DNNs) solve these two problems by extracting effective representations of the target signal from the input mixture. Since essential features of a signal can be well reflected on its latent geometric structure of the feature distribution, a natural way to address SVS/SI is to extract the geometry-aware and distribution-related features of the target signal. To do this, this work introduces the concept of optimal transport (OT) to SVS/SI and proposes an improved optimal transport kernel embedding (iOTKE) to extract the target-distribution-related features. The iOTKE learns an OT from the input signal to the target signal on the basis of a reference set learned from all training data. Thus it can maintain the feature diversity and preserve the latent geometric structure of the distribution for the target signal. To further improve the feature selection ability, we extend the proposed iOTKE to a gated version, i.e., gated iOTKE (G-iOTKE), by incorporating a lightweight gating mechanism. The gating mechanism controls effective information flow and enables the proposed method to select important features for a specific input signal. We evaluated the proposed G-iOTKE on SVS/SI. Experimental results showed that the proposed method provided better results than other models. © 2023 IEEE.

关键词： Embeddings

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：