检索结果-内蒙古大学图书馆

Speech emotion recognition using a novel feature set

Journal of Computational Information Systems 2013年第15期9卷 6097-6104页

作者： Wang, Kunxia Li, Lian Yang, Jing Ren, Fuji Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine Hefei University of Technology Hefei 230000 China School of Electricity and Information Engineering Anhui University of Architecture Hefei 230000 China

Speech emotion recognition has attracted attentions from increased number of researchers in Psychology, Computer science, Phonetics and related disciplines. This paper discusses combining multiple features for speech emotion recognition to yield improved performance. It proposes using combination of multiple features to improve recognition performance. Using ChineseLDC emotional database, the experiment results show that a novel feature set of MFCC, fundamental frequency, Δ MFCC, Δ Δ MFCC, energy, zero-crossing ratio and amplitude can get the best performance as 95% and 84% for emotional speech recognition of four emotional state and six emotional state. © 2013 Binary Information Press.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Combine sentiment lexicon and dependency parsing for sentiment classification

Combine sentiment lexicon and dependency parsing for sentime...

引用

IEEE/SICE International Symposium on System Integration

作者： Changqin Quan Xiquan Wei Fuji Ren Anhui Province Key laboratory of Affective Computing and Advanced Intelligent Machine Hefei University of Technology Hefei China School of Computer and Information Hefei University of Technology Hefei China

With the rapid development of internet technology and e-commerce sites, there are more and more products review in the network. People are willing to make a survey on the internet before purchasing the products. The automatic identification of the sentiment of comments is necessary. We propose a method, which combines sentiment lexicon and dependency parsing to determine the sentiment orientation and the positive or negative attitudes of the topic. The dependency parsing is used to get the objects and sentiment words. Then the allocation of weights is done, and finally the positive and negative results of the products evaluation are concluded. Experiments show that the validity and efficiency of the proposed method.

关键词： Semantics Syntactics Benchmark testing Educational institutions Dictionaries Internet Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Reduce the dimensions of emotional features by principal component analysis for speech emotion recognition

Reduce the dimensions of emotional features by principal com...

引用

IEEE/SICE International Symposium on System Integration

作者： Changqin Quan Dongyu Wan Bin Zhang Fuji Ren AnHui Province Key laboratory of Affective Computing and Advanced Intelligent Machine HeFei University of Technology HeFei China The School of Computer and Information HeFei University of Technology HeFei China

In this paper, the principal component analysis (PCA) is applied to speech emotion recognition for improving the accuracy of the system. The traditional prosodic features like pitch-related features and formant-related features are extracted from the Berlin speech database [7] and a Chinese database. These collected feature data is processed by PCA to remove the irrelevant information. After that, three kinds of features including the processed features by PCA, unprocessed features and other speech-related features are used to train a SVM classifier. And six emotions are tested in the experiment. The classification accuracy of the processed features by PCA is about 3.1% higher than the unprocessed features and about 17.6% higher than the MFCC features when using 240 utterances. The recognition accuracies among different emotions in both databases are also presented in the study.

关键词： Speech Speech recognition Principal component analysis Emotion recognition Feature extraction Accuracy Databases

来源：评论

学校读者我要写书评

暂无评论

Introducing secure data transmission scheme in a heterogeneous environment

Introducing secure data transmission scheme in a heterogeneo...

引用

World Congress on Information and Communication Technologies (WICT)

作者： Kun Liu Kun Ma Ajith Abraham Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan Jinan China IT4Innovations University of Ostrava Czech Republic Machine Intelligence Research Labs (MIR Labs) WA USA

ISBN: (纸本)9781467376396

Various information systems in the heterogeneous environment have resulted in a lot of discrete business data, and this type of storing method decreased the sharing of the data. In this paper, we designed and implement a secure data transmission scheme in the context of High Education Examination Management Information System of Shandong Province (HEEMISSP), in which all kinds of factors in the heterogeneous environment is taken into consideration. We integrate the security certificate technology and the encryption method with the remote method invocation (RMI). Measured by the security, completeness and non-repudiation of data transmission, the design fully satisfied the efficiency of data transmission which is requested by customer.

关键词： Navigation Cryptography Authentication Business Databases Servers Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

A new preprocessing algorithm and local binary pattern based facial expression recognition

A new preprocessing algorithm and local binary pattern based...

引用

IEEE/SICE International Symposium on System Integration

作者： Yao Qian Fuji Ren Changqin Quan Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine Hefei University of Technology Hefei China P. R University of Tokushima Tokushima Japan Hefei University of Technology Hefei Anhui CN

This paper presents a new preprocessing algorithm with local binary pattern for facial expression recognition. Firstly, we establish the skin color model to extract the face region, and then we use the cumulative projection to obtain the completely face region. Secondly, we rotate the inclined faces, normalize all the images, and remove the effect of light to get the required experimental samples. Finally, we use rotation invariance uniform local binary pattern operator to get the facial expression features, and then the support vector machine classifier is used for expression classification. The algorithm is implemented with Matlab and experimented on Indian male facial expression database. The proposed method obtained an accuracy of 72.75% which shows the effectiveness of the proposed algorithm.

关键词： Skin Image color analysis Face Histograms Color Feature extraction Databases

来源：评论

学校读者我要写书评

暂无评论

Microblogging hot events emotion analysis based on Ren-CECps

Microblogging hot events emotion analysis based on Ren-CECps

引用

IEEE/SICE International Symposium on System Integration

作者： Ning Liu Fuji Ren Xiao Sun Changqin Quan AnHui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine HeFei University of Technology HeFei China P.R. The Japan Federation of Engineering Societies University of Tokushima Shinkura-cho Tokushima Japan

Since Sina microblogging was first launched in August 2009, that seems to have become the major social media communication platform in China, microblogging is increasingly deep into life. In this study, we analyze the sentiment of microbloging hot events based on Ren-CECps. According to hot events in chronological, choosing the microblogging hot events of “Beijing Heavy Fog” and “Xi Jinping, Peng Liyuan Visit” for instance, crawling through sina microblogging we can get the corpus that contains the specified events. The method uses word frequency statistics for access microblogging corpus, analyzing trends in specific keywords concerns. At the same time, according to specific keywords related to micro-Bo, we can calculate the emotions of related microblogging via Ren-CECps. Finally, according to changes from time to time, we make a corresponding data charts, visual display of such trends. In this study, we illustrate that we can get a good result of emotion analysis using Ren-CECps in such a microblogging Chinese text with fragmentation and discrete feature. As a further indication of such excellent Chinese emotion corpus, the practical and research value in it are enormous.

关键词： Blogs Market research Educational institutions Kernel Twitter Computers Polynomials

来源：评论

学校读者我要写书评

暂无评论

An experimental investigation on effective friction coefficient in elliptical ultrasonic assisted grinding of monocrystal sapphire

引用

International Journal of Nanomanufacturing 2013年第5-6期9卷 477-485页

作者： Liang, Zhiqiang Wang, Xibin Wu, Yongbo Xie, Lijing Jiao, Li Zhao, Wenxiang Key Laboratory of Fundamental Science for Advanced Machining Beijing Institute of Technology 5 South Zhongguancun Street Haidian District Beijing 100081 China Department of Machine Intelligence and Systems Engineering Akita Prefectural University 84-4 Tsuchiya-ebinokuchi Yurihonjo Akita 015-0055 Japan

In this study, in order to investigate the effective friction coefficient in elliptical ultrasonic assisted grinding (EUAG) of sapphire, the single abrasive grain scratching experiments are performed to simulate the grinding process by setting up the elliptical ultrasonic vibrator attached with the sapphire substrate on a multi-axis CNC grinder. The single grain diamond tool slides on the elliptically vibrated surface at a serial of pressures, and the grinding forces are measured. The friction coefficients under different pressure and vibration amplitude are obtained by calculating the ratio of tangential grinding force to normal grinding force, i.e., Ft /Fn. Comparing friction coefficients in both scratching with and without vibration, there is a critical pressure Fpc at a range of pressure. As the pressure is less than Fpc, the friction coefficient in EUAG is smaller than that in conventional grinding (CG), and once the increasing pressure is more than Fpc, that is much higher than that in CG. When the pressure is slight, ploughing occurs and no chips are generated, and actually at low pressure, the ratio Ft /Fn can be close to the effective friction coefficient in EUAG. Thus, the experimental results at low pressure indicate that the effective friction coefficient in EUAG is less than that in CG, and is decreasing with the increasing vibration amplitude. Copyright © 2013 Inderscience Enterprises Ltd.

关键词： Sapphire

来源：评论

学校读者我要写书评

暂无评论

Feature fusion of HOG and WLD for facial expression recognition

Feature fusion of HOG and WLD for facial expression recognit...

引用

IEEE/SICE International Symposium on System Integration

作者： Xiaohua Wang Chao Jin Wei Liu Min Hu Liangfeng Xu Fuji Ren AnHui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine Hefei University of Technology China School of Computer and Information Hefei University of Technology China The Japan Federation of Engineering Societies University of Tokushima Shinkura-cho Tokushima Japan

A considerable amount of research work has been done for facial expression recognition using local or global feature extraction methods. Weber Local Descriptor (WLD), a simple and robust local image descriptor, is recently developed for local feature extraction. In facial expression recognition, the information contained in the local is important for the recognition result. The Histograms of Oriented Gradients (HOG) can well describe the local area information using gradient and orientation density distribution of the edge. In order to solve the lack of contour and shape information only by WLD features and to extract facial local features more efficiently, we propose a hybrid approach that combines the WLD with HOG features. We divide the images into blocks and weight each of them, then extract the two features and fuse them. At last, the weighted fused histograms are used to classify facial expressions by chi-square distance and the nearest neighbor method. The proposed method is applied on popular JAFFE and Cohn-Kanade facial expression databases and recognition rate is up to 93.97% and 95.86%. Compared with the Gabor Wavelet, LBP, and AAM and experimental results show that the proposed method achieves better performance for facial expression recognition.

关键词： Feature extraction Histograms Databases Face recognition Equations Active appearance model Data mining

来源：评论

学校读者我要写书评

暂无评论

Toward full-text searching middleware over hierarchical documents

Toward full-text searching middleware over hierarchical docu...

引用

International Conference on Intelligent Systems Design and Applications (ISDA)

作者： Kun Ma Bo Yang Ajith Abraham Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan Jinan China IT4 Innovations VSB-Technical University of Ostrava Czech Republic Machine Intelligence Research Labs Scientific Network for Innovation and Research Excellence WA USA

Currently, full-text searching can benefit from the emerging NoSQL databases and traditional indexing tools in the big data era. However, there are some drawbacks of current solutions. On one hand, the indexing documents lack of the hierarchy. On the other hand, big data have become the bottleneck of full-text searching. In the context of big data, we design a full-text searching middleware over hierarchical documents. We discuss the architecture of this middleware in detail. In addition, we propose a structure-independent hierarchical document model to present the hierarchical document. Moreover, the transformation engine is designed to translate the rich files into models. The core log event listener is responsible for capturing the changed documents and push them to the indexing storage at the same time. The experimental results show that our middleware is more advantageous than RDBMS with indexes and RDBMS with Lucene solutions.

关键词： Middleware Engines Real-time systems Indexes Open source software

来源：评论

学校读者我要写书评

暂无评论

EMOTIONAL SPEECH RECOGNITION BASED ON SVM WITH GMM SUPERVECTOR

引用

Journal of Electronics(China) 2012年第3期29卷 339-344页

作者： Chen Yanxiang Xie Jian (Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine School of Computer Science&InformationHefei University of TechnologyHefei 230000China

Emotion recognition from speech is an important field of research in human computer interaction. In this letter the framework of Support Vector machines (SVM) with Gaussian Mixture Model (GMM) supervector is introduced for emotional speech recognition. Because of the importance of variance in reflecting the distribution of speech, the normalized mean vectors potential to exploit the information from the variance are adopted to form the GMM supervector. Comparative experiments from five aspects are conducted to study their corresponding effect to system performance. The experiment results, which indicate that the influence of number of mixtures is strong as well as influence of duration is weak, provide basis for the train set selection of Universal Background Model (UBM).

关键词： Emotional speech recognition Support Vector machines (SVM) Gaussian Mixture Model (GMM) supervector Universal Background Model (USB)

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：