检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

207 篇 期刊文献
131 篇 会议
2 篇 学位论文

馆藏范围

340 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

315 篇 工学
- 176 篇 计算机科学与技术...
- 123 篇 电气工程
- 50 篇 信息与通信工程
- 43 篇 控制科学与工程
- 28 篇 软件工程
- 25 篇 仪器科学与技术
- 21 篇 电子科学与技术（可...
- 18 篇 石油与天然气工程
- 11 篇 动力工程及工程热...
- 10 篇 机械工程
- 8 篇 材料科学与工程（可...
- 8 篇 生物医学工程（可授...
- 6 篇 测绘科学与技术
- 5 篇 土木工程
- 4 篇 建筑学
- 4 篇 化学工程与技术
- 4 篇 生物工程
- 3 篇 力学（可授工学、理...
- 3 篇 船舶与海洋工程
- 3 篇 环境科学与工程（可...
69 篇 理学
- 32 篇 物理学
- 25 篇 生物学
- 9 篇 化学
- 6 篇 数学
- 6 篇 地球物理学
44 篇 医学
- 25 篇 临床医学
- 15 篇 基础医学(可授医学...
- 6 篇 特种医学
23 篇 管理学
- 19 篇 管理科学与工程(可...
5 篇 农学
1 篇 教育学
1 篇 文学
1 篇 艺术学

主题

340 篇 denoising autoen...
64 篇 deep learning
21 篇 convolutional ne...
16 篇 noise reduction
13 篇 neural network
12 篇 machine learning
11 篇 speech recogniti...
10 篇 autoencoder
8 篇 deep neural netw...
8 篇 robust speech re...
7 篇 feature enhancem...
7 篇 transfer learnin...
7 篇 anomaly detectio...
7 篇 missing data
7 篇 neural networks
7 篇 classification
7 篇 unsupervised lea...
6 篇 collaborative fi...
6 篇 fault diagnosis
6 篇 remaining useful...

机构

3 篇 nagaoka univ tec...
3 篇 wuhan univ sch c...
3 篇 acad sinica res ...
2 篇 tsinghua univ de...
2 篇 nanyang technol ...
2 篇 natl taiwan univ...
2 篇 univ calif irvin...
2 篇 univ chinese aca...
2 篇 donald bren scho...
2 篇 nanyang technol ...
2 篇 taiyuan univ tec...
2 篇 harbin inst tech...
2 篇 beijing univ pos...
2 篇 univ sains malay...
2 篇 nanjing univ sci...
2 篇 tsinghua univ de...
2 篇 tech univ libere...
2 篇 natl inst techno...
2 篇 univ calif irvin...
2 篇 city univ hong k...

作者

5 篇 wang longbiao
5 篇 kai atsuhiko
4 篇 tsao yu
4 篇 ueda yuma
3 篇 he fazhi
3 篇 pan yiteng
3 篇 schanze thomas
3 篇 malek jiri
3 篇 li jian
3 篇 samann fars
3 篇 liu bin
2 篇 zhang tao
2 篇 petr cerva
2 篇 kang moses
2 篇 baek jongbok
2 篇 wang huawei
2 篇 wang yuhao
2 篇 padil khairul ha...
2 篇 liu yang
2 篇 teeparthi kiran

语言

328 篇 英文
11 篇 其他
1 篇 中文

检索条件"主题词=Denoising autoencoder"

共 340 条记录，以下是241-250 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

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

A Low-complexity Visual Tracking Approach with Single Hidden Layer Neural Networks 13

A Low-complexity Visual Tracking Approach with Single Hidden...

引用

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

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

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

A Lightweight sequence-based Unsupervised Loop Closure Detection

A Lightweight sequence-based Unsupervised Loop Closure Detec...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Xiong, Fan Ding, Yan Yu, Mingrui Zhao, Wenzhe Zheng, Nanning Ren, Pengju Xi An Jiao Tong Univ Coll Artificial Intelligence Xian Peoples R China

ISBN: (纸本)9780738133669

Stable, effective and lightweight loop closure detection is an always pursued goal in real-time SLAM systems, that can be ported on embedded processors and deployed on autonomous robotics. Deep learning methods have extended the expressive ability and adaptability of the descriptor, and sequence-based methods can greatly improve the matching accuracy. However, the increased computation complexity and storage bandwidth requirements of matching calculations for high-dimensional descriptor make it infeasible for real-time deployment, especially for robots that navigate in relatively big maps. To address this challenge, we propose a lightweight sequence-based unsupervised loop closure detection scheme. To be specific, Principal Component Analysis (PCA) is applied to squeeze the descriptor dimensions while maintaining sufficient expressive ability. Additionally, with the consideration of the image sequence and combining linear query with fast approximate nearest neighbor search to further reduce the execution time and improve the efficiency of sequence matching. We implement our method on CALC, a state-of-the-art unsupervised solution, and conduct experiments on NVIDIA TX2, results demonstrate that the accuracy has been improved by 5%, while the execution speed is 2x faster.

关键词： Simultaneous Localization and Mapping Loop Closure Detection PCA Images Sequence denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

Drone Noise Reduction using Deep Convolutional autoencoder for UAV Acoustic Sensor Networks 16

Drone Noise Reduction using Deep Convolutional Autoencoder f...

引用

16th IEEE International Conference on Mobile Ad Hoc and Smart Systems (IEEE MASS)

作者： Chun, Chanjun Jeon, Kwang Myung Kim, Taewoon Choi, Wooyeol Korea Inst Civil Engn & Bldg Technol Future Infrastruct Res Ctr Goyang 10223 South Korea IntFlow Co Ltd AI Convergence Technol Res Ctr Gwangju 61080 South Korea Hallym Univ Sch Software Chunchon 24252 South Korea Chonsun Univ Dept Comp Engn Gwangju 61452 South Korea

ISBN: (纸本)9781728141213

Drones are widely utilized in various industries. Unfortunately, when a drone acquires sound through a microphone, which is installed itself, drone Hying and wind noises appear in recorded signals. Therefore, it is necessary to reduce such drone flying and wind noises for enhancing the quality of the recorded sound signals for UAV acoustic sensor networks. In this paper, we propose the noise reduction method using a deep convolutional demising autoencoder for eliminating drone flying and wind noises. The deep convolutional denoising autoencoder is widely utilized to extract the target sound source in monaural audio source separation. To do this task, a training dataset is constructed by mixing drone flying and wind noises in clean speech signal. Also, we train the neural network model, which is in form of fully convolutional neural networks. From the sound signals recorded in the real outdoor environment, it is shown that the trained model can reduce the drone flying and wind noises, and only separate the target speech.

关键词： Drone noise noise reduction convolutional neural network denoising autoencoder acoustic sensor network

来源：评论

学校读者我要写书评

暂无评论

Author Identification using Deep Learning 15

Author Identification using Deep Learning

引用

15th IEEE International Conference on Machine Learning and Applications (ICMLA)

作者： Mohsen, Ahmed M. El-Makky, Nagwa M. Ghanem, Nagia Alexandria Univ Fac Engn Alexandria Egypt

ISBN: (纸本)9781509061679

Authorship identification is the task of identifying the author of a given text from a set of suspects. The main concern of this task is to define an appropriate characterization of texts that captures the writing style of authors. Although deep learning was recently used in different natural language processing tasks, it has not been used in author identification (to the best of our knowledge). In this paper, deep learning is used for feature extraction of documents represented using variable size character n-grams. We apply A Stacked denoising autoencoder (SDAE) for extracting document features with different settings, and then a support vector machine classifier is used for classification. The results show that the proposed system outperforms its counterparts

关键词： denoising autoencoder author identification deep learning

来源：评论

学校读者我要写书评

暂无评论

Accurately Clustering Single-cell RNA-seq data by Capturing Structural Relations between Cells through Graph Convolutional Network

Accurately Clustering Single-cell RNA-seq data by Capturing ...

引用

IEEE International Conference on Bioinformatics and Biomedicine (IEEE BIBM)

作者： Zeng, Yuausong Zhou, Xiang Rao, Jiahua Lu, Yutong Yang, Yuedong Sun Yat Sen Univ Sch Data & Comp Sci Guangzhou 510000 Peoples R China Sun Yat Sen Univ Minist Educ Key Lab Machine Intelligence & Adv Comp Guangzhou Peoples R China

ISBN: (纸本)9781728162157

Recent advances in single-cell RNA sequencing (scRNA-seq) technologies provide a great opportunity to study gene expression at cellular resolution, and the scRNA-seq data has been routinely conducted to unfold cell heterogeneity and diversity. A critical step for the scRNA-seq analyses is to cluster the same type of cells, and many methods have been developed for cell clustering. However, existing clustering methods are limited to extract the representations from expression data of individual cells, while ignoring the high-order structural relations between cells. Here, we proposed a new method (GraphSCC) to cluster cells based on scRNA-seq data by accounting structural relations between cells through a graph convolutional network. The representation learned from the graph convolutional network, together with another representation output from a denoising autoencoder network, are optimized by a dual self-supervised module for better cell clustering. Extensive experiments indicate that GraphSCC model outperforms state-of-the-art methods in various evaluation metrics on both simulated and real datasets.

关键词： Graph Convolutional Network Single-cell RNA-seq Clustering denoising autoencoder Self-supervised Learning

来源：评论

学校读者我要写书评

暂无评论

Recognition of mild-to-moderate depression based on facial expression and speech 24

Recognition of mild-to-moderate depression based on facial e...

引用

5th International Conference on Computing, Networks and Internet of Things (CNIOT)

作者： Li, Jinlong Li, Ying Lanzhou Inst Technol Coll Elect Informat Engn Lanzhou Peoples R China

ISBN: (纸本)9798400716751

The behavioral symptoms of patients with mild to moderate depression (MMD) are usually not obvious enough, which poses a challenge to MMD recognition research. A three-level feature construction strategy for facial expression was proposed to fully characterize the differences in facial activity between MMD patients and healthy control groups (HCs). Level 1: Construct geometric features to describe facial activity preliminarily. Level 2: Input geometric features into a denoising autoencoder (DAE) to generate a new hidden layer representation. Level 3: Gaussian mixture model (GMM) further characterizes the hidden layer features. Meanwhile, a speech feature set was constructed based on the fundamental frequency (F0), pitch intensity, mel frequency cepstral coefficients (MFCCs), and syllable pauses of speech. Finally, facial expression and speech were fused at the feature layer, and MMD recognition was carried out based on four classic classification algorithms. The experimental results show that the MMD recognition accuracy of the male and female groups can reach 70.3% and 68.3%, respectively.

关键词： Depression recognition Facial expression Speech denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

S-VECTOR: A DISCRIMINATIVE REPRESENTATION DERIVED FROM I-VECTOR FOR SPEAKER VERIFICATION 23

S-VECTOR: A DISCRIMINATIVE REPRESENTATION DERIVED FROM I-VEC...

引用

23rd European Signal Processing Conference (EUSIPCO)

作者： Isik, Yusuf Ziya Erdogan, Hakan Sarikaya, Ruhi TUBITAK BILGEM Gebze Turkey Sabanci Univ Fac Engn & Nat Sci Istanbul Turkey Microsoft Corp Redmond WA 98052 USA

ISBN: (纸本)9780992862633

Representing data in ways to disentangle and factor out hidden dependencies is a critical step in speaker recognition systems. In this work, we employ deep neural networks (DNN) as a feature extractor to disentangle and emphasize the speaker factors from other sources of variability in the commonly used i-vector features. denoising autoencoder based unsupervised pre-training, random dropout fine-tuning, and Nesterov accelerated gradient based momentum is used in DNN training. Replacing the i-vectors with the resulting speaker vectors (s-vectors), we obtain superior results on NIST SRE corpora on a wide range of operating points using probabilistic linear discriminant analysis (PLDA) back-end.

关键词： speaker verification denoising autoencoder random dropout

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共34页 << < 21 22 23 24 25 26 27 28 29 30 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：