检索结果-内蒙古大学图书馆

13th International Conference on Control Automation Robotics & Vision (ICARCV)

作者： Dai, Liang Zhu, Yuesheng Luo, Guibo He, Chao Peking Univ Shenzhen Grad Sch Inst Big Data Technol Lab Commun & Informat Secur Beijing Peoples R China

ISBN: (纸本)9781479951994

Visual tracking algorithms based on deep learning have robust performance against variations in a complex environment because deep learning can learn generic features from numerous unlabeled images. However, due to the multi-layer architecture, the deep learning trackers suffer from expensive computational costs and are not suitable for real-time applications. In this paper, a low-complexity visual tracking scheme with single hidden layer neural network is proposed based on denoising autoencoder. To further reduce the computational costs, feature selection is applied to simplify the networks and two optimization methods are used during the online tracking process. The experimental results have demonstrated that the proposed algorithm is about six times faster than the trackers based on deep nets and rapid enough for real-time applications with encouraging accuracy.

关键词： visual tracking neural network denoising autoencoder single hidden layer

来源：评论

学校读者我要写书评

暂无评论

An Agreement Based Dynamic Routing Method for Fault Diagnosis in Power Network with Enhanced Noise Immunity 31

An Agreement Based Dynamic Routing Method for Fault Diagnosi...

引用

31st Australasian Universities Power Engineering Conference (AUPEC)

作者： Fahim, Shahriar Rahman Muyeen, S. M. Sarker, Yeahia Sarker, Subrata K. Das, Sajal K. Amer Int Univ Bangladesh Dhaka 1229 Bangladesh Qatar Univ Doha 2713 Qatar Rajshahi Univ Engn & Technol Rajshahi 6204 Bangladesh

ISBN: (纸本)9781665434515

The stable operation of a power system often depends on inscribing the faults that may arise when transmitting and distributing electrical power. Characterizing these faults is necessary to analyze the post-fault oscillography of the power lines. The power lines are prone to be affected by noises. The noises are responsible to introduce uncertainty in operating conditions. The variation in operating conditions leads to an unbalanced system. The diagnosis of faults is essential to ensure the secured operation of a power network. This paper introduces a unified unsupervised learning framework for short circuit fault analysis of a power transmission line. The proposed approach works with a small number of data set and reduces the computational cost. It uses a capsule network that investigates the low-level fault-oriented features. To guarantee the robustness of the proposed framework against noises a stacked denoising-autoencoder is integrated and modeled. The performance of the proposed model is measured and compared with some of the techniques available in the literature in terms of noise. The test with field data for three types of fault classification results in an accuracy of 9 ms for fault triggering.

关键词： Faults transmission line Capsule network time series imaging vector denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

SEPARATION MATRIX OPTIMIZATION USING ASSOCIATIVE MEMORY MODEL FOR BLIND SOURCE SEPARATION 23

SEPARATION MATRIX OPTIMIZATION USING ASSOCIATIVE MEMORY MODE...

引用

23rd European Signal Processing Conference (EUSIPCO)

作者： Omachi, Motoi Ogawa, Tetsuji Kobayashi, Tetsunori Fujieda, Masaru Katagiri, Kazuhiro Waseda Univ Dept Comp Sci Tokyo Japan Oki Elect Ind Co Ltd Minato Tokyo Japan

ISBN: (纸本)9780992862633

A source signalis estimated using an associative memory model (AMM) and used for separation matrix optimization in linear blind source separation (BSS) to yield high quality and less distorted speech. Linear-filtering-based BSS, such as independent vector analysis (IVA), has been shown to he effective in sound source separation while avoiding non-linear signal distortion. This technique, however, requires several assumptions of sound sources being independent and generated from non-Gaussian distribution. We propose a method for estimating a linear separation matrix without, any assumptions about the sources by repeating the following two steps: estimating non-distorted reference signals by using an AMM and optimizing the separation matrix to minimize an error between the estimated signal and reference signal. Experimental comparisons carried out in simultaneous speech separation suggest that the proposed method can reduce the residual distortion caused by IVA.

关键词： convolutional neural network denoising autoencoder associative memory model linear filtering blind source separation

来源：评论

学校读者我要写书评

暂无评论

ROBUST RECOGNITION OF SPEECH WITH BACKGROUND MUSIC IN ACOUSTICALLY UNDER-RESOURCED SCENARIOS

ROBUST RECOGNITION OF SPEECH WITH BACKGROUND MUSIC IN ACOUST...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Malek, Jiri Zdansky, Jindrich Cerva, Petr Tech Univ Liberec Fac Mechatron Informat & Interdisciplinary Studie Studentska 2 Liberec 46117 Czech Republic

ISBN: (纸本)9781538646588

This paper addresses the task of Automatic Speech Recognition (ASR) with music in the background. We consider two different situations: 1) scenarios with very small amount of labeled training utterances (duration 1 hour) and 2) scenarios with large amount of labeled training utterances (duration 132 hours). In these situations, we aim to achieve robust recognition. To this end we investigate the following techniques: a) multi-condition training of the acoustic model, b) denoising autoencoders for feature enhancement and c) joint training of both above mentioned techniques. We demonstrate that the considered methods can be successfully trained with the small amount of labeled acoustic data. We present substantially improved performance compared to acoustic models trained on clean speech. Further, we show a significant increase of accuracy in the under-resourced scenario, when utilizing additional amount of non-labeled data. Here, the non-labeled dataset is used to improve the accuracy of the feature enhancement via autoencoders. Subsequently, the autoencoders are jointly fine-tuned along with the acoustic model using the small amount of labeled utterances.

关键词： robust speech recognition feature enhancement denoising autoencoder multi-condition training joint training

来源：评论

学校读者我要写书评

暂无评论

Bottleneck Features from SNR-Adaptive denoising Deep Classifier for Speaker Identification

Bottleneck Features from SNR-Adaptive Denoising Deep Classif...

引用

Asia-Pacific-Signal-and-Information-Processing-Association Annual Summit and Conference (APSIPA ASC)

作者： Tan, Zhili Mak, Man-Wai Hong Kong Polytech Univ Dept Elect & Informat Engn Ctr Signal Proc Hong Kong Hong Kong Peoples R China

ISBN: (纸本)9789881476807

In this paper, we explore the potential of using deep learning for extracting speaker-dependent features for noise robust speaker identification. More specifically, an SNR-adaptive denoising classifier is constructed by stacking two layers of restricted Boltzmann machines (RBMs) on top of a denoising deep autoencoder, where the top-RBM layer is connected to a soft-max output layer that outputs the posterior probabilities of speakers and the top-RBM layer outputs speaker-dependent bottleneck features. Both the deep autoencoder and RBMs are trained by contrastive divergence, followed by backpropagation fine-tuning. The autoencoder aims to reconstruct the clean spectra of a noisy test utterance using the spectra of the noisy test utterance and its SNR as input. With this denoising capability, the output from the bottleneck layer of the classifier can be considered as a low-dimension representation of denoised utterances. These frame-based bottleneck features are than used to train an iVector extractor and a PLDA model for speaker identification. Experimental results based on a noisy YOHO corpus show that the bottleneck features slightly outperform the conventional MFCC under low SNR conditions and that fusion of the two features lead to further performance gain, suggesting that the two features are complementary with each other.

关键词： Deep learning Bottleneck features denoising autoencoder speaker identification deep belief networks

来源：评论

学校读者我要写书评

暂无评论

MULTI-TASK autoencoder FOR NOISE-ROBUST SPEECH RECOGNITION

MULTI-TASK AUTOENCODER FOR NOISE-ROBUST SPEECH RECOGNITION

引用

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Zhang, Haoyi Liu, Conggui Inoue, Nakamasa Shinoda, Koichi Tokyo Inst Technol Tokyo Japan

ISBN: (纸本)9781538646588

For speech recognition in noisy environments, we propose a multi-task autoencoder which estimates not only clean speech features but also noise features from noisy speech. We introduce the deSpeeching autoencoder, which excludes speech signals from noisy speech, and combine it with the conventional denoising autoencoder to form a unified multi-task autoencoder (MTAE). We evaluate it using the Aurora 2 dataset and CHIME 3 dataset. It reduced WER by 15.7% from the conventional denoising autoencoder in the Aurora 2 test set A.

关键词： denoising autoencoder deSpeeching autoencoder robust speech recognition

来源：评论

学校读者我要写书评

暂无评论

Frequency Offset Correction in Single Sideband(SSB) Speech by Deep Neural Network for Speaker Verification 16

Frequency Offset Correction in Single Sideband(SSB) Speech b...

引用

16th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2015)

作者： Xing, Hua Liu, Gang Hansen, John H. L. Univ Texas Dallas Ctr Robust Speech Syst Richardson TX 75083 USA

ISBN: (纸本)9781510817906

Communication system mismatch represents a major influence for loss in speaker recognition performance. This paper considers a type of nonlinear communication system mismatch- modulation/demodulation (Mod/DeMod) carrier drift in single side band (SSB) speech signals. We focus on the problem of estimating frequency offset in SSB speech in order to improve speaker verification performance of the drifted speech. Based on a two-step framework from previous work, we propose using a multi-layered neural network architecture, stacked denoising autoencoder (SDA), to determine the unique interval of the offset value in the first step. Experimental results demonstrate that the SDA based system can produce up to a +16.1% relative improvement in frequency offset estimation accuracy. A speaker verification evaluation shows a +65.9% relative improvement in EER when SSB speech signal is compensated with the frequency offset value estimated by the proposed method.

关键词： frequency offset single sideband speaker verification denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

Microscopic biopsy image reconstruction using inception block with denoising auto-encoder approach

引用

International Journal of Information Technology (Singapore) 2024年第4期16卷 2413-2423页

作者： Singh, Shiksha Kumar, Rajesh Department of Electronics & Communication JK Institute of Applied Physics & Technology University of Allahabad UP Prayagraj India

The use of computer-aided image analysis for disease diagnosis and prognosis has dramatically increased during the past 10 years. The introduction of computer-assisted image analysis of images produced by equipment employed in medical science for the prognosis of various diseases has been made possible by the development of digital scanners and high-resolution imaging technologies. Additionally, much like any other digital image, the obtained medical images may become distorted by various distortions and sounds. The noise in histopathology images can be random or have an even frequency distribution;it can be introduced during data acquisition by imaging devices or as a result of signal processing algorithms;either way, the noise appears in the digital image in an uncorrelated way, inevitably lowering the visual quality of the images. In the present article, employed an integrative strategy for the image denoising of the histopathological images of Breast cancer through deep learning (DL) approach. Moreover, some noises remain intact while following the approach due to the direct conduction of the feature map and also the level noise. Henceforth, a denoising model using denoising autoencoder with an Inception network block (InDAENET) has been proposed to deal with the left-out feature maps and high noise signals related to the medical images. The proposed method has been prepared and verified on the publicly available dataset BreakHis. This approach has further been successfully compared with the conventional denoising autoencoder (DAE) method. Henceforth, it paves the way for Histopathological Image Reconstruction using an Inception block with denoising autoencoder for Breast Cancer Detection. © 2024, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of Computer Applications and Management.

关键词： Convolutional neural network denoising autoencoder Histopathological image Inception network Medical image

来源：评论

学校读者我要写书评

暂无评论

Self-supervised Siamese autoencoders 22nd

Self-supervised Siamese Autoencoders

引用

22nd International Symposium on Intelligent Data Analysis (IDA)

作者： Baier, Friederike Mair, Sebastian Fadel, Samuel G. Leuphana Univ Luneburg Luneburg Germany Uppsala Univ Uppsala Sweden Linkoping Univ Linkoping Sweden

ISBN: (纸本)9783031585463;9783031585470

In contrast to fully-supervised models, self-supervised representation learning only needs a fraction of data to be labeled and often achieves the same or even higher downstream performance. The goal is to pre-train deep neural networks on a self-supervised task, making them able to extract meaningful features from raw input data afterwards. Previously, autoencoders and Siamese networks have been successfully employed as feature extractors for tasks such as image classification. However, both have their individual shortcomings and benefits. In this paper, we combine their complementary strengths by proposing a new method called SidAE (Siamese denoising autoencoder). Using an image classification downstream task, we show that our model outperforms two self-supervised baselines across multiple data sets and scenarios. Crucially, this includes conditions in which only a small amount of labeled data is available. Empirically, the Siamese component has more impact, but the denoising autoencoder is nevertheless necessary to improve performance.

关键词： Self-supervised learning representation learning Siamese networks denoising autoencoder pre-training image classification

来源：评论

学校读者我要写书评

暂无评论

A Collaborative Framework Using Multimodal Data and Adaptive Noise for Human Behavior Anomaly Detection

A Collaborative Framework Using Multimodal Data and Adaptive...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Yang, Guoqing Gao, Jianzhe Zhang, Kejia He, Yifan Luo, Zhiming Li, Shaozi Xiamen Univ Dept Artif Intelligence Xiamen Peoples R China Wuyi Univ Fujian Key Lab Big Data Applicat & Intellectualiz Wuyishan Peoples R China

ISBN: (纸本)9798350359329;9798350359312

Human behavior anomaly detection in video aims to identify unusual behaviors that are crucial for public safety. Recently, there has been an increase in reconstruction or predictionbased methods that integrate diverse modal features to enhance anomaly detection. However, they use methods that independently or directly fusion multimodal features without fully considering the collaborative potential between multimodal features, which are susceptible to interference from semantic differences, thereby impacting detection performance. In contrast, we design a collaborative framework using multimodal data and adaptive noise for behavior anomaly detection. Our framework detects anomalies by analyzing the contrastive differences between two modalities alongside single-frame reconstruction errors. Specifically, we first learn the correlation between RGB and skeletal modalities for normal behavior through contrastive learning and use inter-modal contrast difference to detect motion anomalies. Additionally, we propose a single-frame reconstruction network that adaptively adds noise based on the importance of foreground features to detect appearance anomalies. Anomalies often occur in the motion foreground, and increasing noise in this area can make it more difficult to reconstruct anomalies. Extensive experiments validate the state-of-the-art performance of our method on three public datasets.

关键词： Human behavior anomaly detection Multimodal feature Contrastive learning denoising autoencoder

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：