检索结果-南通市图书馆

Speech Enhancement via Mask-Mapping Based residual dense Network

Computers, Materials & Continua 2023年第1期74卷 1259-1277页

作者： Lin Zhou Xijin Chen Chaoyan Wu Qiuyue Zhong Xu Cheng Yibin Tang School of Information Science and Engineering Southeast UniversityNanjing210096China Center for Machine Vision and Signal Analysis University of OuluOuluFI-90014Finland College of IOT Engineering Hohai UniversityChangzhou213022China

Masking-based and spectrum mapping-based methods are the two main algorithms of speech enhancement with deep neural network(DNN).But the mapping-based methods only utilizes the phase of noisy speech,which limits the upper bound of speech enhancement *** methods need to accurately estimate the masking which is still the key *** the advantages of above two types of methods,this paper proposes the speech enhancement algorithm MM-RDN(maskingmapping residual dense network)based on masking-mapping(MM)and residual dense network(RDN).Using the logarithmic power spectrogram(LPS)of consecutive frames,MM estimates the ideal ratio masking(IRM)matrix of consecutive *** can make full use of feature maps of all ***,using the global residual learning to combine the shallow features and deep features,RDN obtains the global dense features from the LPS,thereby improves estimated accuracy of the IRM *** show that the proposed method achieves attractive speech enhancement performance in various acoustic ***,in the untrained acoustic test with limited priors,e.g.,unmatched signal-to-noise ratio(SNR)and unmatched noise category,MM-RDN can still outperform the existing convolutional recurrent network(CRN)method in themeasures of perceptual evaluation of speech quality(PESQ)and other evaluation *** indicates that the proposed algorithm is more generalized in untrained conditions.

关键词： Mask-mapping-based method residual dense block speech enhancement

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Speech Enhancement via residual dense Generative Adversarial Network

引用

Computer Systems Science & Engineering 2021年第9期38卷 279-289页

作者： Lin Zhou Qiuyue Zhong Tianyi Wang Siyuan Lu Hongmei Hu School of Information Science and Engineering Southeast UniversityNanjing210096China Medizinische Physik and Cluster of Excellence“Hearing4all” Department of Medical Physics and AcousticsUniversity of Oldenburg26129OldenburgGermany

Generative adversarial networks(GANs)are paid more attention to dealing with the end-to-end speech enhancement in recent *** GANbased enhancement methods are presented to improve the quality of reconstructed ***,the performance of these GAN-based methods is worse than those of masking-based *** tackle this problem,we propose speech enhancement method with a residual dense generative adversarial network(RDGAN)contributing to map the log-power spectrum(LPS)of degraded speech to the clean *** detail,a residual dense block(RDB)architecture is designed to better estimate the LPS of clean speech,which can extract rich local features of LPS through densely connected convolution ***,sequential RDB connections are incorporated on various scales of *** significantly increases the feature learning flexibility and robustness in the time-frequency *** show that the proposed method achieves attractive speech enhancement performance in various acoustic ***,in the untrained acoustic test with limited priors,e.g.,unmatched signal-to-noise ratio(SNR)and unmatched noise category,RDGAN can still outperform the existing GAN-based methods and masking-based method in the measures of PESQ and other evaluation *** indicates that our method is more generalized in untrained conditions.

关键词： Generative adversarial networks neural networks residual dense block speech enhancement

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Advanced Generative Adversarial Network for Image Superresolution

引用

国际计算机前沿大会会议论文集 2022年第1期 193-208页

作者： Mei Jia Mingde Lu Yu Sang School of Electronic and Information Engineering Liaoning Technical UniversityHuludao 125105China Institute of Computing Technology Research Institute of Liaohe Oilfield CompanyPanjin 124010China

The superresolution(SR)method based on generative adversarial networks(GANs)cannot adequately capture enough diversity from training data,resulting in misalignment between input low resolution(LR)images and output high resolution(HR)*** training has difficulty *** on this,an advanced GAN-based image SR reconstructionmethod is ***,the dense connection residual block and attention mechanism are integrated into the GAN generator to improve high-frequency feature ***,an added discriminator is added into the GAN discriminant network,which forms a dual discriminator to ensure that the process of training is ***,the more robust Charbonnier loss is used instead of the mean square error(MSE)loss to compare similarities between the obtained image and actual image,and the total variation(TV)loss is employed to smooth the training ***,the experimental results indicate that global structures can be better reconstructed using the method of this paper and texture details of images compared with other SOTA *** peak signal-to-noise ratio(PSNR)values by the method of this paper are improved by an average of 2.24 dB,and the structural similarity index measure(SSIM)values are improved by an average of 0.07.

关键词： Generative adversarial networks(GANs) Superresolution(SR) residual dense block Attention mechanism Dual discriminator

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Underwater Image Enhancement Based on Multi-scale Adversarial Network

引用

印刷与数字媒体技术研究 2024年第5期 70-77页

作者： ZENG Jun-yang SI Zhan-jun College of Light Industry Science and Engineering Tianjin University of Science and TechnologyTianjin 300457China College of Artificial Intelligence Tianjin University of Science and TechnologyTianjin 300457China

In this study,an underwater image enhancement method based on multi-scale adversarial network was proposed to solve the problem of detail blur and color distortion in underwater ***,the local features of each layer were enhanced into the global features by the proposed residual dense block,which ensured that the generated images retain more ***,a multi-scale structure was adopted to extract multi-scale semantic features of the original ***,the features obtained from the dual channels were fused by an adaptive fusion module to further optimize the *** discriminant network adopted the structure of the Markov *** addition,by constructing mean square error,structural similarity,and perceived color loss function,the generated image is consistent with the reference image in structure,color,and *** experimental results showed that the enhanced underwater image deblurring effect of the proposed algorithm was good and the problem of underwater image color bias was effectively *** both subjective and objective evaluation indexes,the experimental results of the proposed algorithm are better than those of the comparison algorithm.

关键词： Underwater image enhancement Generative adversarial network Multi-scale feature extraction residual dense block

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

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：