检索结果-内蒙古大学图书馆

IEEE Transactions on Audio, Speech and Language processing 2025年 33卷 2045-2058页

作者： Yiming Zhang Xuenan Xu Ruoyi Du Haohe Liu Yuan Dong Zheng-Hua Tan Wenwu Wang Zhanyu Ma Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Centre for Vision Speech and Signal Processing University of Surrey Guildford U.K. Department of Electronic Systems Aalborg University Aalborg Denmark

In traditional audio captioning methods, a model is usually trained in a fully supervised manner using a human-annotated dataset containing audio-text pairs and then evaluated on the test set from the same dataset. Such methods have two limitations. First, these methods are often data-hungry and require time-consuming and expensive human annotations to obtain audio-text pairs. Second, these models often suffer from performance degradation in cross-domain scenarios, i.e., when the input audio comes from a different domain than the training set, and this issue has received little attention. To address these issues, we propose a new zero-shot method for audio captioning. Our method is built on the contrastive language-audio pre-training (CLAP) model. During training, the model reconstructs the ground-truth caption using the CLAP text encoder. In the inference stage, the model generates text descriptions from the CLAP audio embeddings of given audio inputs. To enhance the ability of the model in transitioning from text-to-text generation to audio-to-text generation, we propose to use the mixed-augmentations-based soft prompt to learn more robust latent representations, leveraging instance replacement and embedding augmentation. Additionally, we introduce the retrieval-based acoustic-aware hard prompt to improve the cross-domain performance of the model by employing the domain-agnostic label information of sound events. Extensive experiments on AudioCaps and Clotho benchmarks show the effectiveness of our proposed method, which outperforms other zero-shot audio captioning approaches for in-domain scenarios and outperforms the compared methods for cross-domain scenarios, underscoring the generalization ability of our method.

关键词： Training Decoding Semantics Data models Acoustics Electronic mail Benchmark testing Transformers Robustness Perturbation methods

来源：评论

学校读者我要写书评

暂无评论

Metasurface-Loaded Circularly Polarized Dual-Band MIMO Cellphone Frame Antenna for Mobile Communication Applications

引用

IEEE Antennas and Wireless Propagation Letters 2025年

作者： Meng, Yanfeng Ren, Aidi Wang, Chao Xu, Guanghui Zhao, Luyu Li, Yingsong Yang, Lixia Huang, Zhi-Xiang Anhui University Information Materials and Intelligent Sensing Laboratory of Anhui Province Hefei230039 China Anhui University School of Electronic and Information Engineering Hefei230601 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Hefei230039 China Anhui Province Key Laboratory of Target Recognition and Feature Extraction Anhui237010 China Anhui University Key Laboratory of Electromagnetic Environment al Sensing of Anhui Higher Education Institutes Hefei230039 China

In this letter, a set of circularly polarized (CP) multiple-input multiple-output (MIMO) cellphone frame antennas for mobile communication applications is proposed. The planar inverted-F antenna (PIFA) and monopole antenna operate at frequencies of 3.5 GHz and 5.5 GHz with impedance and axial ratio (AR) bandwidths overlapping at 11.4% (3.3-3.7 GHz) and 7.3% (5.2-5.6 GHz), respectively. To reduce the electromagnetic coupling between the two antennas, the V-shaped mental fence is added and different rectangular metasurface (RMS) arrays are adopted to enhance the CP radiation performances. This design not only covers 5G communication, LTE, and the 5 GHz Wi-Fi band. It also provides a communication strategy for future direct satellite communication from cellphones, enhancing efficient switching between satellite and cellular networks. © 2002-2011 IEEE.

关键词： Monopole antennas

来源：评论

学校读者我要写书评

暂无评论

Online radar screening pulse width allocation Strategy Based on Non-stationary Bandit

引用

Digital signal processing 2025年

作者： Hongyu Zhu Yefei Wang Rong Xie Zheng Liu Shuwen Xu Lei Ran National Key Laboratory of Radar Signal Processing Xidian University Xi’an 710071 China Multisensor Intelligent Detection and Recognition Technologies R&D Center of CASC Chengdu 610100 China

With the development of jamming technologies, jammers can respond to radar signals within a short period, causing radar frequency-hopping strategies to fail. In the face of jammers with instantaneous frequency measurements (IFM) capabilities, radio frequency (RF) screening techniques are an effective countermeasure. However, in practice, the jamming strategy is usually unknown to the radar. Moreover, when the jammer's strategy changes, failing to promptly adjust the shielding pulse parameters will result in a significant degradation of the RF screening anti-jamming effectiveness. To overcome the limitations caused by the lack of information about the jammer and the non-stationary environment due to changes in the jammer's IFM time, this paper proposes an online radar screening pulse width allocation method based on a non-stationary multi-armed bandit (MAB). This method combines discounted historical rewards and sliding window rewards, allowing it to better adapt to the non-stationary jamming environment. Simulation results show that the proposed method has a faster convergence speed than the discounted method and a stronger exploration capability than the sliding window method. It can effectively enhance radar performance in countering instantaneous frequency measuring jammers in non-stationary jamming environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Short Review on Industrial Prognostic Hybrid Approaches: Concepts, Techniques and Applications 12

A Short Review on Industrial Prognostic Hybrid Approaches: C...

引用

2024 12th International Conference on Systems and Control, ICSC 2024

作者： Bouzenita, M. Mouss, L.-H. Melgani, F. Bentrcia, T. Batna Algeria University of Trento The Laboratory of Signal Processing and Recognition Trento38123 Italy

ISBN: (纸本)9798331531812

In the present work, we provide a short literature review on prognostics hybrid approaches as recently emerged in a wide range of industrial applications. In this context, we cover the main concepts of the prognostics field, different aspects of prognostic hybrid approaches in addition to basic benchmarks employed during the evaluation of hybrid approaches. We finally conclude with some observations and guidelines. We would like to mention that all these aspects were justified with appropriate up to date sources. © 2024 IEEE.

关键词： Benchmark Data driven approach Experience based approach Hybrid approach Physics based approach Prognostics and health management

来源：评论

学校读者我要写书评

暂无评论

Image-based algorithm for the catheter recognition based on GLCM 28

Image-based algorithm for the catheter recognition based on ...

引用

28th International Conference on Computer Graphics and Vision, GraphiCon 2018

作者： Danilov, V.V. Skirnevskiy, I.P. Manakov, R.A. Gerget, O.M. Melgani, F. Medical Devices Design Laboratory Tomsk Polytechnic University Tomsk Russia Signal Processing and Recognition Laboratory University of Trento Trento Italy

The focus of this study was to develop an image-based algorithm for the catheter detection. Epicardial full-volume 3D echocardiography datasets were used as an input data of the algorithm. In total, 9 datasets consisted of 15 three-dimensional timeframes were processed. To correctly detect the catheter, the feature-based approach was applied to recognition the catheter within the 3D echocardiography datasets. The algorithm based on gray-level co-occurrence matrix (GLCM) was applied as a feature extraction technique. Once the GLCM was computed, we obtained correlation, contrast, homogeneity and energy features. Then we applied feature thresholds to the catheter detection. These thresholds were obtained using Support Vector Machine (SVM) with the linear kernel function and standardization the predictor data. The average segmentation and recognition accuracies of the algorithm equal 94.16% and 87.2% respectively. The processing time for one 2D slice and one 3D dataset are equal to 9±0.2 milliseconds and 1.96±0.045 seconds, respectively. Though the algorithm is not time-consuming for 2D mode, it is still complicated to apply it for real-time surgery in 3D mode. © GraphiCon 2018 - 28th International Conference on Computer Graphics and Vision. All rights reserved.

关键词： Catheters

来源：评论

学校读者我要写书评

暂无评论

Optimal ν-SVM parameter estimation using multi objective evolutionary algorithms

Optimal ν-SVM parameter estimation using multi objective ev...

引用

2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010

作者： Ethridge, James Ditzler, Gregory Polikar, Robi Dept. of Electrical and Computer Engineering Rowan University Signal Processing and Pattern Recognition Laboratory Glassboro NJ 08028 United States

ISBN: (纸本)9781424469109

Using a machine learning algorithm for a given application often requires tuning design parameters of the classifier to obtain optimal classification performance without overfitting. In this contribution, we present an evolutionary algorithm based approach for multi-objective optimization of the sensitivity and specificity of a ν-SVM. The ν-SVM is often preferred over the standard C-SVM due to smaller dynamic range of the ν parameter compared to the unlimited dynamic range of the C parameter. Instead of looking for a single optimization result, we look for a set of optimal solutions that lie along the Pareto optimality front. The traditional advantage of using the Pareto optimality is of course the flexibility to choose any of the solutions that lies on the Pareto optimality front. However, we show that simply maximizing sensitivity and specificity over the Pareto front leads to parameters that appear to be mathematically optimal yet still cause overfitting. We propose a multiple objective optimization approach with three objective functions to find additional parameter values that do not cause overfitting. © 2010 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Robust speech recognition using adaptive noise threshold estimation and wavelet shrinkage

Robust speech recognition using adaptive noise threshold est...

引用

HUT-ICCE 2008 - 2nd International Conference on Communications and Electronics

作者： Tuan, Van Pham Kubin, Gernot Rank, Erhard Signal Processing and Speech Communication Laboratory Graz University of Technology Graz Austria Research and Development Philips Speech Recognition Systems Vienna Austria

ISBN: (纸本)9781424424269

We propose an improved noise reduction method for robust speech recognition based on a perceptually statistical wavelet filtering algorithm. Perceptual noise thresholds are estimated from the universal thresholds for each critical wavelet subband. Fast changes of background noise are tracked adaptively by improving our statistical percentile filtering method. Smoothed wavelet shrinkage is applied to enhance noisy wavelet coefficients. Performance of the proposed denoising algorithm is evaluated in terms of recognition performance under adverse noisy conditions such as car and factory environments. Furthermore, it is compared to recent speech enhancement methods embedded in different state-of-theart speech recognizers. Overall results indicate that almost similar recognition performance is obtained on the AURORA3 SPEECHDAT-Car corpus as compared to the HTK recognizer using the advanced front-end while there is an improvement when testing with the Loquendo recognizer on the SNOW-Factory corpus. ©2008 IEEE.

关键词： Noise abatement

来源：评论

学校读者我要写书评

暂无评论

STRNet:Triple-stream Spatiotemporal Relation Network for Action recognition

引用

International Journal of Automation and computing 2021年第5期18卷 718-730页

作者： Zhi-Wei Xu Xiao-Jun Wu Josef Kittler School of Artificial Intelligence and Computer Science Jiangnan UniversityWuxi 214122China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Wuxi 214122China Centre for Vision Speech and Signal ProcessingUniversity of SurreyGuildfordGU27XHUK

Learning comprehensive spatiotemporal features is crucial for human action recognition. Existing methods tend to model the spatiotemporal feature blocks in an integrate-separate-integrate form, such as appearance-and-relation network(ARTNet) and spatiotemporal and motion network(STM). However, with blocks stacking up, the rear part of the network has poor interpretability. To avoid this problem, we propose a novel architecture called spatial temporal relation network(STRNet), which can learn explicit information of appearance, motion and especially the temporal relation information. Specifically, our STRNet is constructed by three branches,which separates the features into 1) appearance pathway, to obtain spatial semantics, 2) motion pathway, to reinforce the spatiotemporal feature representation, and 3) relation pathway, to focus on capturing temporal relation details of successive frames and to explore long-term representation dependency. In addition, our STRNet does not just simply merge the multi-branch information, but we apply a flexible and effective strategy to fuse the complementary information from multiple pathways. We evaluate our network on four major action recognition benchmarks: Kinetics-400, UCF-101, HMDB-51, and Something-Something v1, demonstrating that the performance of our STRNet achieves the state-of-the-art result on the UCF-101 and HMDB-51 datasets, as well as a comparable accuracy with the state-of-the-art method on Something-Something v1 and Kinetics-400.

关键词： Action recognition spatiotemporal relation multi-branch fusion long-term representation video classification

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Learning in Initially Labeled Non-Stationary Environments with Gradual Drift

Semi-Supervised Learning in Initially Labeled Non-Stationary...

引用

International Joint Conference on Neural Networks

作者： Karl B. Dyer Robi Polikar Signal Processing & Pattern Recognition Laboratory Rowan University

ISBN: (纸本)9781467314886

Semi-supervised learning (SSL) in non-stationary environments has received relatively little attention in machine learning, despite a growing number of applications that can benefit from a properly configured SSL algorithm. Previous works in learning non-stationary data have analyzed such cases where both labeled and unlabeled instances are received at every time step and/or in regular intervals;however, to the best of our knowledge, no work has investigated the case where labeled instances are received only at the initial time step, followed by unlabeled instances provided in subsequent time steps. In this proof-of-concept work, we propose a new framework for learning in a non-stationary environment that provides only unlabeled data after the initial time step, to which we refer to as initially labeled environment. The proposed framework generates labels for previously unlabeled data at each time step to be combined with incoming unlabeled data - possibly from a drifting distribution - using a compacted polytope sample extraction algorithm. We have conducted two experiments to demonstrate the feasibility and reliability of the approach. This proof-of-concept is presented in two dimensions;however, the algorithm can be extended to higher dimensions with appropriate modifications.

关键词： Alpha shape Concept drift Non-stationary environment Shape offsets Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

An Optimization Method Based on Deep Learning for Electromagnetic Inverse Scattering Problems

An Optimization Method Based on Deep Learning for Electromag...

引用

2024 International Applied Computational Electromagnetics Society Symposium, ACES-China 2024

作者： Hu, Wangchao Xie, Guoda Dai, Jinpeng Hou, Guilin Li, Xiang Huang, Zhixiang Anhui University The Key Laboratory of Intelligent Computing and Signal Processing Hefei China Anhui Province Key Laboratory of Target Recognition and Feature Extraction Education of Anhui Province Luan237000 China Ministry of Education The Key Laboratory of Intelligent Computing and Signal Processing Hefei China Anhui Province Anhui University Key Laboratory of Electromagnetic Environmental Sensing Hefei230601 China Anhui University Hefei China

ISBN: (纸本)9798350355581

In this paper, a deep learning optimization method combining U-net model and cycle generative adversarial network (Cycle-GAN) is proposed to efficiently solve the electromagnetic inverse scattering (EMIS) problems. Firstly, a U-net model is used to obtain a rough preliminary reconstruction. Through down-sampling and up-sampling processes, the basic features of the object are extracted and reconstructed from the measured scattered field, providing a coarse dielectric parameter distribution. Then, a Cycle-GAN model further refines the output of the U-net. The Cycle-GAN model, through its adversarial training mechanism involving a generator and a discriminator, enhances the details of the preliminary reconstruction, resulting in a finely detailed dielectric parameter distribution his method improves the problem of rough results obtained by using U-net method alone, and can effectively solve and optimize EMIS problems. © 2024 IEEE.

关键词： Generative adversarial networks

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：