检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and signal processing, ICASSP 2025

作者： Fan, Shitong Xiao, Feiyang Wang, Wenbo Qi, Shuhan Zhu, Qiaoxi Wang, Wenwu Guan, Jian Group of Intelligent Signal Processing Harbin Engineering University Harbin China Faculty of Computing Harbin Institute of Technology Harbin China School of Computer Science and Technology Harbin Institute of Technology Shenzhen China Acoustics Lab University of Technology Sydney Ultimo Australia Centre for Vision Speech and Signal Processing University of Surrey Guildford United Kingdom

ISBN: (纸本)9798350368741

Microphone array techniques are widely used in sound source localization and smart city acoustic-based traffic monitoring, but these applications face significant challenges due to the scarcity of lab.led real-world traffic audio data and the complexity and diversity of application scenarios. The DCASE Challenge's Task 10 focuses on using multi-channel audio signals to count vehicles (cars or commercial vehicles) and identify their directions (left-to-right or vice versa). In this paper, we propose a graph-enhanced dual-stream feature fusion network (GEDF-Net) for acoustic traffic monitoring, which simultaneously considers vehicle type and direction to improve detection. We propose a graph-enhanced dual-stream feature fusion strategy which consists of a vehicle type feature extraction (VTFE) branch, a vehicle direction feature extraction (VDFE) branch, and a frame-level feature fusion module to combine the type and direction feature for enhanced performance. A pre-trained model (PANNs) is used in the VTFE branch to mitigate data scarcity and enhance the type features, followed by a graph attention mechanism to exploit temporal relationships and highlight important audio events within these features. The frame-level fusion of direction and type features enables fine-grained feature representation, resulting in better detection performance. Experiments demonstrate the effectiveness of our proposed method. GEDF-Net is our submission that achieved 1st place in the DCASE 2024 Challenge Task 10. © 2025 IEEE.

关键词： Acoustic-based traffic monitoring feature fusion graph attention pre-trained model transfer learning

来源：评论

学校读者我要写书评

暂无评论

Attacking Voice Anonymization Systems with Augmented Feature and Speaker Identity Difference

Attacking Voice Anonymization Systems with Augmented Feature...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Yanzhe Zhang Zhonghao Bi Feiyang Xiao Xuefeng Yang Qiaoxi Zhu Jian Guan Group of Intelligent Signal Processing College of Computer Science and Technology Harbin Engineering University China Faculty of Computing Harbin Institute of Technology China Acoustics Lab University of Technology Sydney Australia

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

This study focuses on the First VoicePrivacy Attacker Challenge within the ICASSP 2025 signal processing Grand Challenge, which aims to develop speaker verification systems capable of determining whether two anonymized speech signals are from the same speaker. However, differences between feature distributions of original and anonymized speech complicate this task. To address this challenge, we propose an attacker system that combines Data Augmentation enhanced feature representation and Speaker Identity Difference enhanced classifier to improve verification performance, termed DA-SID. Specifically, data augmentation strategies (i.e., data fusion and SpecAugment) are utilized to mitigate feature distribution gaps, while probabilistic linear discriminant analysis (PLDA) is employed to further enhance speaker identity difference. Our system significantly outperforms the baseline, demonstrating exceptional effectiveness and robustness against various voice anonymization systems, ultimately securing a top-5 ranking in the challenge.

关键词： Data privacy Data integration signal processing Data augmentation Probabilistic logic Robustness Linear discriminant analysis Information filtering Speech processing Information integrity

来源：评论

学校读者我要写书评

暂无评论

Graph-Enhanced Dual-Stream Feature Fusion with Pre-Trained Model for Acoustic Traffic Monitoring

Graph-Enhanced Dual-Stream Feature Fusion with Pre-Trained M...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Shitong Fan Feiyang Xiao Wenbo Wang Shuhan Qi Qiaoxi Zhu Wenwu Wang Jian Guan Group of Intelligent Signal Processing Harbin Engineering University Harbin China Faculty of Computing Harbin Institute of Technology Harbin China School of Computer Science and Technology Harbin Institute of Technology Shenzhen China Acoustics Lab University of Technology Sydney Ultimo Australia Centre for Vision Speech and Signal Processing University of Surrey Guildford UK

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Microphone array techniques are widely used in sound source localization and smart city acoustic-based traffic monitoring, but these applications face significant challenges due to the scarcity of lab.led real-world traffic audio data and the complexity and diversity of application scenarios. The DCASE Challenge’s Task 10 focuses on using multi-channel audio signals to count vehicles (cars or commercial vehicles) and identify their directions (left-to-right or vice versa). In this paper, we propose a graph-enhanced dual-stream feature fusion network (GEDF-Net) for acoustic traffic monitoring, which simultaneously considers vehicle type and direction to improve detection. We propose a graph-enhanced dual-stream feature fusion strategy which consists of a vehicle type feature extraction (VTFE) branch, a vehicle direction feature extraction (VDFE) branch, and a frame-level feature fusion module to combine the type and direction feature for enhanced performance. A pre-trained model (PANNs) is used in the VTFE branch to mitigate data scarcity and enhance the type features, followed by a graph attention mechanism to exploit temporal relationships and highlight important audio events within these features. The frame-level fusion of direction and type features enables fine-grained feature representation, resulting in better detection performance. Experiments demonstrate the effectiveness of our proposed method. GEDF-Net is our submission that achieved 1st place in the DCASE 2024 Challenge Task 10.

关键词： Location awareness Smart cities signal processing Feature extraction Acoustics Data models Microphone arrays Speech processing Monitoring Faces

来源：评论

学校读者我要写书评

暂无评论

Disentangling Hierarchical Features for Anomalous Sound Detection Under Domain Shift

arXiv

引用

arXiv 2025年

作者： Guan, Jian Tian, Jiantong Zhu, Qiaoxi Xiao, Feiyang Zhang, Hejing Liu, Xubo Group of Intelligent Signal Processing College of Computer Science and Technology Harbin Engineering University Harbin150001 China Acoustics Lab. University of Technology Sydney UltimoNSW2007 Australia Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

Anomalous sound detection (ASD) encounters difficulties with domain shift, where the sounds of machines in target domains differ significantly from those in source domains due to varying operating conditions. Existing methods typically employ domain classifiers to enhance detection performance, but they often overlook the influence of domain-unrelated information. This oversight can hinder the model’s ability to clearly distinguish between domains, thereby weakening its capacity to differentiate normal from abnormal sounds. In this paper, we propose a Gradient Reversal-based Hierarchical feature Disentanglement (GRHD) method to address the above challenge. GRHD uses gradient reversal to separate domain-related features from domain-unrelated ones, resulting in more robust feature representations. Additionally, the method employs a hierarchical structure to guide the learning of fine-grained, domain-specific features by leveraging availab.e metadata, such as section IDs and machine sound attributes. Experimental results on the DCASE 2022 Challenge Task 2 dataset demonstrate that the proposed method significantly improves ASD performance under domain shift. Copyright © 2025, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A contrastive learning framework of graph reconstruction and hypergraph learning for key node identification

引用

Chaos, Solitons and Fractals 2025年 197卷

作者： Huang, Xu-Dong Zhang, Xian-Jie Zhang, Hai-Feng Data Intelligence Lab Research Center For Data To Cyberspace School of Cyber Science and Technology University of Science and Technology of China Hefei Anhui230026 China The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Mathematical Science Anhui University Hefei Anhui230601 China

With the emergence of complex networks in various domains, the key node identification has become one of the critical issues that needs to be studied. Traditional index methods typically focus on single structural information, while existing data-driven approaches often rely solely on the intrinsic lower-order features of nodes. However, assessing the importance of nodes requires a comprehensive consideration of both network structures and higher-order features from multiple perspectives. To address these challenges, this paper proposes a novel deep learning framework based on Graph Reconstruction and Hypergraph Contrastive Learning, termed GRHCL. The GRHCL method constructs hypergraph structures from original graphs using random walks, followed by leveraging graph reconstruction and hypergraph learning methods to capture both structural and higher-order embedding features of nodes. Positive and negative node pairs are then constructed across different views for contrastive learning. Finally, the model is trained using a training sample set obtained through a clustering sampling strategy, along with a joint loss function. Comparative experiments against various baseline methods demonstrate that the GRHCL method achieves superior predictive performance with smaller training sets, improving accuracy by over 5% on some datasets compared to the next best-performing method. © 2025 Elsevier Ltd

关键词： Clustering sampling Contrastive learning Graph reconstruction learning Hypergraph learning Key node identification

来源：评论

学校读者我要写书评

暂无评论

A Miniaturized Bandwidth Reconfigurable Bandpass Chip Filter with Semi-lumped Topology and GaAs pHEMT Technology

引用

Chinese Journal of Electronics 2021年第1期30卷 192-198页

作者： LI Linqing ZHU Haoran NING Xingyu LI Zunwen WU Xianliang Key Lab of Intelligent Computing and Signal Processing Ministry of Education Anhui University

A miniaturized reconfigurable bandpass chip filter with semi-lumped topology and Gallium Arsenide pseudomorphic High electron mobility transistor（GaAs pHEMT） technology is proposed. Semi-lumped topology is employed to instead the traditional lumped inductor with microstrip transmission line, which can reduced the size of the tunable filter significantly. Three-order series and shunt resonated bandpass filter is implemented with shorted stubs and metal-insulator-metal capacitors. Two transmission zeros are introduced with the series resonator and the shunted GaAs FET. By tuning the gate bias circuit of the FET, the capacitance of the series resonator is changed and the bandwidth of the filter is adjusted correspondingly. An equivalent circuit model is developed to interpret the mechanism of the proposed filter circuit. A reconfigurable on chip filter sample operated at 10 GHz is fabricated to validate the design. Two fractional bandwidth of 14.3% and 23.5% are tuned with bias voltage of the FET, while insertion loss of 2.4 d B and 2.2 d B are observed with the filter, respectively. The area of the chip filter is 0.86 × 0.96 mm2and is equivalent to an electrical length of 0.08 × 0.09λg2at center frequency. Measurement results agree well with the simulation ones.

关键词： gallium arsenide tunable filter transmission zeros equivalent circuit model resonator filters shunted FET III-V semiconductors miniaturized bandwidth reconfigurable bandpass chip filter MIM devices microstrip transmission line chip filter sample shunt resonated bandpass filter metal-insulator-metal capacitors semilumped topology loss 2.4 dB Gallium Arsenide pseudomorphic High electron mobility transistor technology insertion loss filter circuit integrated circuit design GaAs integrated circuit manufacture frequency 10.0 GHz pHEMT technology microwave filters loss 2.2 dB HEMT integrated circuits series resonator miniaturized reconfigurable bandpass chip filter band-pass filters

来源：评论

学校读者我要写书评

暂无评论

A full-rate cooperative relay transmission scheme with randomized cyclic delay diversity

引用

Journal of Computational Information Systems 2014年第1期10卷 275-284页

作者： Xu, Lei Bao, Menglin Jiang, Ran Zhang, Hongwei Li, Xiaohui Key Lab. of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei 230039 China

Randomized cyclic delay diversity (RCDD) is an effective means to capture both the space diversity and the frequency diversity with low complexity detection over frequency-selective fading channels. Since many existing full-rate cooperative relay transmission schemes have the disadvantages of low spectrum efficiency and high complexity detection, a practical and low complexity detection full-rate distributed cooperative relay transmission scheme is proposed in this paper by taking advantages of the randomized cyclic delay diversity method and the linear constellation precoding (LCP) technology. The bit error rate (BER) performance of the proposed scheme is superior to that of the system with fixed cyclic delay diversity (FCDD) when the number of subcarriers is sufficiently large. Moreover, the system diversity gain improves with the multipath number of the frequency-selective fading channel and the relay number increases. Copyright © 2014 Binary Information Press.

关键词： Cooperative communication

来源：评论

学校读者我要写书评

暂无评论

A full-rate and low-detection complexity cooperative transmission scheme with cyclic delay diversity

引用

Journal of Computational Information Systems 2013年第11期9卷 4593-4600页

作者： Xu, Lei Wang, Li Zhang, Hongwei Li, Xiaohui Key Lab. of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei 230039 China

The use of orthogonal channels for the cooperative transmission results in a loss of rate or spectral efficiency, and the exiting full-rate cooperative transmission schemes based on space-time code design have the defect of high detection complexity. Therefore, by adopting the non-orthogonal amplify and forward (NAF) mode, combining with the advantages of linear constellation precoding (LCP) technique and cyclic delay diversity (CDD) technique in this paper, a new full-rate wireless cooperative transmission scheme designed based on space-time-frequency codes is proposed. Compared with the existing full-rate cooperative transmission scheme, this new scheme is suitable for multi-relay scenario, and has the advantages of simple structure, low signal detection complexity which does not increase with the relay number. Compared with the equal power allocation scheme, the optimal power allocation scheme can make the system bit error rate (BER) performance improved. © 2013 by Binary Information Press.

关键词： Spectrum efficiency

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Covering Algorithm

引用

Tsinghua Science and Technology 2014年第1期19卷 76-81页

作者： Jie Chen Shu Zhao Yanping Zhang Department of Computer Science and Technology and Key Lab of Intelligent Computing and Signal Processing Anhui University

The concept of deep learning has been applied to many domains, but the definition of a suitable problem depth has not been sufficiently explored. In this study, we propose a new Hierarchical Covering Algorithm （HCA） method to determine the levels of a hierarchical structure based on the Covering Algorithm （CA）. The CA constructs neural networks based on samples＇ own characteristics, and can effectively handle multi-category classification and large-scale data. Further, we abstract characters based on the CA to automatically embody the feature of a deep structure. We apply CA to construct hidden nodes at the lower level, and define a fuzzy equivalence relation R on upper spaces to form a hierarchical architecture based on fuzzy quotient space theory. The covering tree naturally becomes from R. HCA experiments performed on MNIST dataset show that the covering tree embodies the deep architecture of the problem, and the effects of a deep structure are shown to be better than having a single level.

关键词： deep architecture hierarchy fuzzy equivalence relation covering tree MNIST dataset

来源：评论

学校读者我要写书评

暂无评论

MICkNN:Multi-Instance Covering kNN Algorithm

引用

Tsinghua Science and Technology 2013年第4期18卷 360-368页

作者： Shu Zhao Chen Rui Yanping Zhang Department of Computer Science and Technology and Key Lab of Intelligent Computing and Signal Processing Anhui University

Mining from ambiguous data is very important in data mining. This paper discusses one of the tasks for mining from ambiguous data known as multi-instance problem. In multi-instance problem, each pattern is a lab.led bag that consists of a number of unlab.led instances. A bag is negative if all instances in it are negative. A bag is positive if it has at least one positive instance. Because the instances in the positive bag are not lab.led, each positive bag is an ambiguous. The mining aim is to classify unseen bags. The main idea of existing multi-instance algorithms is to find true positive instances in positive bags and convert the multi-instance problem to the supervised problem, and get the lab.ls of test bags according to predict the lab.ls of unknown instances. In this paper, we aim at mining the multi-instance data from another point of view, i.e., excluding the false positive instances in positive bags and predicting the lab.l of an entire unknown bag. We propose an algorithm called Multi-Instance Covering kNN （MICkNN） for mining from multi-instance data. Briefly, constructive covering algorithm is utilized to restructure the structure of the original multi-instance data at first. Then, the kNN algorithm is applied to discriminate the false positive instances. In the test stage, we lab.l the tested bag directly according to the similarity between the unseen bag and sphere neighbors obtained from last two steps. Experimental results demonstrate the proposed algorithm is competitive with most of the state-of-the-art multi-instance methods both in classification accuracy and running time.

关键词： mining ambiguous data multi-instance classification constructive covering algorithm kNN algorithm

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：