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

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

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

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

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

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

Adaptive facial expression recognition based on a weighted component and global features

Adaptive facial expression recognition based on a weighted c...

引用

4th International Conference on Digital Home, ICDH 2012

作者： Li, Rui Hu, Min Wang, XiaoHua Xu, Liangfeng Huang, Zhong Chen, Xing AnHui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine School of Computer and Information Hefei University of Technology Hefei China School of Computer and Information Hefei University of Technology Hefei China

ISBN: (纸本)9781467313483

An adaptive facial expression recognition method based on component and global features is presented in this paper. The facial component features are highlighted for purpose of improving facial expression percent correct rate. Firstly, eyebrows, eyes, nose and mouth are divided from a facial expression image and then the component features would be gotten from these organ images which are processed by Gabor wavelets. The weighted adaptive algorithm would be used to calculate the component feature weights, the weighted component features fuse with the global feature to get a feature fusion matrix. Finally, Weighted Principal Component Analysis (WPCA) and Fisher Linear Discriminant (FLD) methods are used to reduce dimensions and classify facial expression. Experimental results show that the algorithm proposed in this paper has much more accurate recognition rate compared with the global Gabor wavelets, PCA and FLD integrated algorithm. © 2012 IEEE.

关键词： Adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

A MMSM-based Hybrid Method for Chinese MicroBlog Word Segmentation 2

A MMSM-based Hybrid Method for Chinese MicroBlog Word Segmen...

引用

2nd CIPS-SIGHAN Joint Conference on Chinese Language Processing, CLP 2012

作者： Sun, Xiao Li, Chengcheng Tang, Chenyi Ye, Jiaqi AnHui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine School of Computer and Information Hefei University of Technology Anhui Hefei230009 China School of Computer Science and Engineering Dalian University of Technology Liaoning Dalian116023 China

After years of researches, Chinese word segmentation has achieved quite high precisions for formal style text. However, the performance of segmentation is not so satisfying for MicroBlog corpora. In this paper we describe a scheme for Chinese word segmentation for, MicroBlog which integrates the character-based and word-based information in the directed graph generated by MMSM model. Word-level information is effective for analysis of known words, while character-level information is useful for analysis of unknown words. A multi-chain unequal states CRF model is proposed. The proposed multi-chain unequal states CRF has two state chains with unequal states which can recognize the POS tag simultaneously. The hybrid model was effective and adopted in real-world system. © 2021 CLP 2012 - 2nd CIPS-SIGHAN Joint Conference on Chinese Language Processing. All Rights Reserved.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

Differently implicational α-universal triple I restriction method of (1, 2, 2) type

引用

Journal of Systems Engineering and Electronics 2012年第4期23卷 560-573页

作者： Yiming Tang Fuji Ren Yanxiang Chen Information and Communication Engineering Postdoctoral Research Station Hefei University of TechnologyHefei 230009P.R.China State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100191P.R.China Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine Hefei University of TechnologyHefei 230009P.R.China Institute of Technology and Science The University of TokushimaMinami Josanjima770-8506Japan

From the viewpoints of both fuzzy system and fuzzy reasoning, a new fuzzy reasoning method which contains the α- triple I restriction method as its particular case is proposed. The previous α-triple I restriction principles are improved, and then the optimal restriction solutions of this new method are achieved, especially for seven familiar implications. As its special case, the corresponding results of α-triple I restriction method are obtained and improved. Lastly, it is found by examples that this new method is more reasonable than the α-triple I restriction method.

关键词： fuzzy reasoning fuzzy system triple I method triple Irestriction method compositional rule of inference method.

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：