Class-specific multiple classifiers scheme to recognize emotions from speech signals

Automatic emotion recognition from speech signals is one of the important research areas, which adds value to machine intelligence. Pitch, duration, energy and Mel-frequency cepstral coefficients (MFCC) are the widely used features in the field of speech emotion recognition. A single classifier or a combination of classifiers is used to recognize emotions from the input features. The present work investigates the performance of the features of Autoregressive (AR) parameters, which include gain and reflection coefficients, in addition to the traditional linear prediction coefficients (LPC), to recognize emotions from speech signals. The classification performance of the features of AR parameters is studied using discriminant, k-nearest neighbor (KNN), Gaussian mixture model (GMM), back propagation artificial neural network (ANN) and support vector machine (SVM) classifiers and we find that the features of reflection coefficients recognize emotions better than the LPC. To improve the emotion recognition accuracy, we propose a class-specific multiple classifiers scheme, which is designed by multiple parallel classifiers, each of which is optimized to a class. Each classifier for an emotional class is built by a feature identified from a pool of features and a classifier identified from a pool of classifiers that optimize the recognition of the particular emotion. The outputs of the classifiers are combined by a decision level fusion technique. The experimental results show that the proposed scheme improves the emotion recognition accuracy. Further improvement in recognition accuracy is obtained when the scheme is built by including MFCC features in the pool of features.     

基于SVM-KNN算法的情绪脑电识别

情绪识别与日常生活的诸多领域都有很大联系.然而,通过单一算法难以获得较高的情绪识别准确率,为此,提出一种基于支持向量机(support vector machine,SVM)和K近邻(K-nearest neighbors,KNN)融合算法(SVM-KNN)的情绪脑电识别模型.在情绪分类时,首先计算待识别样本与最优分类...     

Employing hierarchical Bayesian networks in simple and complex emotion topic analysis

Traditional emotion models, when tagging single emotions in documents, often ignore the fact that most documents convey complex human emotions. In this paper, we join emotion analysis with topic models to find complex emotions in documents, as well as the intensity of the emotions, and study how the document emotions vary with topics. Hierarchical Bayesian networks are employed to generate the latent topic variables and emotion variables. On average, our model on single emotion classification outperforms the traditional supervised machine learning models such as SVM and Naive Bayes. The other model on the complex emotion classification also achieves promising results. We thoroughly analyze the impact of vocabulary quality and topic quantity to emotion and intensity prediction in our experiments. The distribution of topics such as Friend and Job are found to be sensitive to the documents’ emotions, which we call emotion topic variation in this paper. This reveals the deeper relationship between topics and emotions.     

Extracting common emotions from blogs based on fine-grained sentiment clustering

Recently, blogs have emerged as the major platform for people to express their feelings and sentiments in the age of Web 2.0. The common emotions, which reflect people’s collective and overall sentiments, are becoming the major concern for governments, business companies and individual users. Different from previous literatures on sentiment classification and summarization, the major issue of common emotion extraction is to find out people’s collective sentiments and their corresponding distributions on the Web. Most existing blog clustering methods take into account keywords, stories or timelines but neglect the embedded sentiments, which are considered very important features of blogs. In this paper, a novel method based on Probabilistic Latent Semantic Analysis (PLSA) is presented to model the hidden sentiment factors and an emotion-oriented clustering approach is proposed to find common emotions according to the fine-grained sentiment similarity between blogs. Extensive experiments are conducted on real-world datasets consisting of different topics. The results show that our approach can partition blogs into sentiment coherent clusters and the extracted common emotion words afford good navigation guidelines for embedded sentiments in each cluster.     

A BDI approach to infer student’s emotions in an intelligent learning environment

In this article we describe the use of mental states approach, more specifically the belief-desire-intention (BDI) model, to implement the process of affective diagnosis in an educational environment. We use the psychological OCC model, which is based on the cognitive theory of emotions and is possible to be implemented computationally, in order to infer the learner’s emotions from his actions in the system interface. In our work we profit from the reasoning capacity of the BDI model in order to infer the student’s appraisal (a cognitive evaluation of a person that elicits an emotion), which allows us to deduce student’s emotions. The system reasons about an emotion-generating situation and tries to infer the user’s emotion by using the OCC model. Besides, the BDI model is very adequate to infer and also model students affective states since the emotions have a dynamic nature.     

基于多级SVM分类的语音情感识别算法

为了提高语音情感识别系统的识别准确率,本文在传统支持向量机(SVM)方法的基础之上,提出了一种基于PCA的多级SVM情感分类算法。首先将容易区分的情感分开,针对混淆度大且不能再利用多级分类策略直接进行区分的情感,采用主成分分析法(PCA)进行特征降维,然后逐级地判断出输入语音所属的情感类型。与传统基于SVM分类算法的语音情感识别相比,本文提出的方法可将7种情感的平均识别率提高5.05%,并且特征维度可降低58.3%,从而证明了本文所提出的方法的正确性与有效性。     

基于传递熵关键因果连接的情感识别方法

人脑在情绪活动中呈现的信息流是复杂多变的,因此理解脑区间的动态交互过程至关重要,但是基于原始脑电信号构建的情绪网络包含了许多与情绪无关的冗余信息.针对此问题,提出一种在不丢失关键因果信息的前提下去除情绪无关网络连接的方法,并验证其在情感识别过程中的有效性.首先,基于传递熵因果分析方法对积极、中性和消极情绪构建归一化传递熵矩阵,再从积极、消极情绪矩阵中减去中性情绪矩阵,最后基于简化后的矩阵构建因效性脑网络并利用图论分析不同情绪的网络连通性.通过在DEAP数据集上的验证发现,该方法有效地提高了情感识别准确率.     

基于DBN的多特征融合音乐情感分类方法

本文在音乐情感分类中的两个重要的环节：特征选择和分类器上进行了探索.在特征选择方面基于传统算法中单一特征无法全面表达音乐情感的问题,本文提出了多特征融合的方法,具体操作方式是用音色特征与韵律特征相结合作为音乐情感的符号表达;在分类器选择中,本文采用了在音频检索领域表现较好的深度置信网络进行音乐情感训练和分类.实验结果表明,该算法对音乐情感分类的表现较好,高于单一特征的分类方法和SVM分类的方法.     

基于过程神经元的语音情感识别的建模与仿真

为克服由传统语音情感识别模型的缺陷导致的识别正确率不高的问题,将过程神经元网络引入到语音情感识别中来。通过提取基频、振幅、音质特征参数作为语音情感特征参数,利用小波分析去噪,主成分分析（PCA）消除冗余,用过程神经元网络对生气、高兴、悲伤和惊奇四种情感进行识别。实验结果表明,与传统的识别模型相比,使用过程神经元网络具有较好的识别效果。     

使用二次特征选择及核融合的语音情感识别

为提高语音情感识别精度,对基本声学特征构建的多维特征集合,采用二次特征选择方法综合考虑特征参数与情感类别之间的内在特性,从而建立优化的、具有有效情感可分性的特征子集;在语音情感识别阶段,设计二叉树结构的多分类器以综合考虑系统整体性能与复杂度,采用核融合方法改进SVM模型,使用多核SVM识别混淆度最大的情感。算法在Berlin情感语音库五种情感状态的样本上进行验证,实验结果表明二次特征选择与核融合相结合的方法在有效提高情感识别精度的同时,对噪声具有一定的鲁棒性。     

基于多流CNN-LSTM网络的群体情绪识别

群体情绪识别是人机交互领域的前言课题,针对群体情绪识别准确率的问题,结合卷积神经网络（CNN）与长短期记忆网络（LSTM）,提出一种多流CNN-LSTM网络模型学习群体情绪的静态和动态特征。以视频序列的原始图像、视觉显著图形和叠加的光流图像分别作为三个通道的输入,利用CNN网络对空间特征和局部运动特征进行分析,得到的特征图直接输入LSTM网络,进行全局运动特征的学习。最后连接Softmax分类器,对三个通道的Softmax输出进行加权融合,得到分类结果。实验结果表明,本文模型可有效地识别4种典型的群体情绪,且识别率高于已有算法,准确度（ACC）和宏平均精度（MAP）分别最高可达82.6%、84.1%。     

Transitive node similarity: predicting and recommending links in signed social networks

Online social networks (OSNs) like Facebook, Myspace, and Hi5 have become popular, because they allow users to easily share content. OSNs recommend new friends to registered users based on local features of the graph (i.e., based on the number of common friends that two users share). However, OSNs do not exploit the whole structure of the network. Instead, they consider only pathways of maximum length 2 between a user and his candidate friends. On the other hand, there are global approaches, which detect the overall path structure in a network, being computationally prohibitive for huge-size social networks. In this paper, we define a basic node similarity measure that captures effectively local graph features (i.e., by measuring proximity between nodes). We exploit global graph features (i.e., by weighting paths that connect two nodes) introducing transitive node similarity. We also derive variants of our method that apply to different types of networks (directed/undirected and signed/unsigned). We perform extensive experimental comparison of the proposed method against existing recommendation algorithms using synthetic and real data sets (Facebook, Hi5 and Epinions). Our experimental results show that our FriendTNS algorithm outperforms other approaches in terms of accuracy and it is also time efficient. Finally, we show that a significant accuracy improvement can be gained by using information about both positive and negative edges.     

基于粗集的表情识别在电力学习中的应用

本文提出了一种基于粗集的自动表情识别系统(RAFERS),该系统首先对人脸表情进行预处理,然后依次进行特征提取、特征选择、训练情感分类模型,并将该系统实际应用于电力知识学习系统,对电力知识学习的用户进行人脸表情的自动识别,进而为用户提供个性化的服务。     

基于交互注意力机制的多模态情感识别算法

在多模态语音情感识别中,现有的研究通过提取大量特征来识别情感,但过多的特征会导致关键特征被淹没在相对不重要特征里,造成关键信息遗漏.为此提出了一种模型融合方法,通过两种注意力机制来寻找可能被遗漏的关键特征.本方法在IEMOCAP数据集上的四类情感识别准确率相比现有文献有明显提升;在注意力机制可视化下,两种注意力机制分别找到了互补且对人类情感识别重要的关键信息,从而证明了所提方法相比传统方法的优越性.     

基于ConvLSTM网络的维度情感识别模型研究

学业情绪能够影响和调节学习者的注意、记忆、思维等认知活动,情绪自动识别是智慧学习环境中情感交互和教学决策的基础。目前情绪识别研究主要集中在离散情绪的识别,其在时间轴上是非连续的,无法精准刻画学生学业情绪演变过程,为解决这个问题,基于众包方法建立真实在线学习情境中的中学生学习维度情感数据集,设计基于连续维度情感预测的深度学习分析模型。实验中根据学生学习风格确定触发学生学业情绪的学习材料,并招募32位实验人员进行自主在线学习,实时采集被试面部图像,获取157个学生学业情绪视频;对每个视频进行情感Arousal和Valence二维化,建立包含2 178张学生面部表情的维度数据库;建立基于ConvLSTM网络的维度情感模型,并在面向中学生的维度情感数据库上进行实验,得到一致性相关系数（Concordance Correlation Coefficient,CCC）均值为0.581,同时在Aff-Wild公开数据集上进行实验,得到的一致相关系数均值为0.222。实验表明,提出的基于维度情感模型在Aff-Wild公开数据集维度情绪识别中CCC相关度系数指标提升了7.6%~43.0%。     

基于PAD理论的人脸情感识别

情感计算的一个重要任务是情感建模。提出了在人脸情感的视觉识别范畴中基于PAD理论的情感建模。根据Mehrabian提出的PAD 3维情感理论,建立了EBM(emotional block model)模型,进行了非典型情感识别的尝试。采用88特征点的Gabor特征和SVM算法在Cohn-Kanade数据集上进行了非典型情感识别以及典型情感识别的实验,并就典型情感的识别与基本情感模型比较。实验结果表明,无论是识别非典型情感还是典型情感,基于PAD理论建立的情感模型都是可靠的。在会聚度高的情感子空间上的识别率比会聚度低的情感子空间高。     

Segment-based emotion recognition from continuous Mandarin Chinese speech

Recognition of emotion in speech has recently matured to one of the key disciplines in speech analysis serving next generation human-machine interaction and communication. However, compared to automatic speech recognition, that emotion recognition from an isolated word or a phrase is inappropriate for conversation. Because a complete emotional expression may stride across several sentences, and may fetch-up on any word in dialogue. In this paper, we present a segment-based emotion recognition approach to continuous Mandarin Chinese speech. In this proposed approach, the unit for recognition is not a phrase or a sentence but an emotional expression in dialogue. To that end, the following procedures are presented: First, we evaluate the performance of several classifiers in short sentence speech emotion recognition architectures. The results of the experiments show that the WD-KNN classifier achieves the best accuracy for the 5-class emotion recognition what among the five classification techniques. We then implemented a continuous Mandarin Chinese speech emotion recognition system with an emotion radar chart which is based on WD-KNN; this system can represent the intensity of each emotion component in speech. This proposed approach shows how emotions can be recognized by speech signals, and in turn how emotional states can be visualized.     

语音情感的维度特征提取与识别

研究了情绪的维度空间模型与语音声学特征之间的关系以及语音情感的自动识别方法。介绍了基本情绪的维度空间模型,提取了唤醒度和效价度对应的情感特征,采用全局统计特征减小文本差异对情感特征的影响。研究了生气、高兴、悲伤和平静等情感状态的识别,使用高斯混合模型进行4种基本情感的建模,通过实验设定了高斯混合模型的最佳混合度,从而较好地拟合了4种情感在特征空间中的概率分布。实验结果显示,选取的语音特征适合于基本情感类别的识别,高斯混合模型对情感的建模起到了较好的效果,并且验证了二维情绪空间中,效价维度上的情感特征对语音情感识别的重要作用。     

融合背景上下文特征的视觉情感识别与预测方法

为解决基于视觉的情感识别无法捕捉人物所处环境和与周围人物互动对情感识别的影响、单一情感种类无法更丰富地描述人物情感、无法对未来情感进行合理预测的问题,提出了融合背景上下文特征的视觉情感识别与预测方法。该方法由融合背景上下文特征的情感识别模型（Context-ER）和基于GRU与Valence-Arousal连续情感维度的情感预测模型（GRU-mapVA）组成。Context-ER同时综合了面部表情、身体姿态和背景上下文（所处环境、与周围人物互动行为）特征,进行26种离散情感类别的多标签分类和3个连续情感维度的回归。GRU-mapVA根据所提映射规则将Valence-Arousal的预测值投影到改进的Valence-Arousal模型上,使得情感预测类间差异更为明显。Context-ER在Emotic数据集上进行了测试,结果表明,识别情感的平均精确率比现有最优方法提高4%以上;GRU-mapVA在三段视频样本上进行了测试,结果表明情感预测效果相较于现有方法有很大提升。     

Mutual influences between message volume and emotion intensity on emerging infectious diseases: An investigation with microblog data

The dynamic interdependence between microblog volume and emotions expressed in message content has been largely underexplored. To understand the public’s reaction to emerging infectious diseases, we draw upon theories in psychology and social media, and propose that there is a cyclical relationship between message volume and the intensity of emotions (positive or negative) in which they influence each other positively over time. Furthermore, negative and positive emotions mutually suppress each other, yet are autocorrelated, respectively. Relying on more than 560,000 microblogs collected from Sina Weibo between February 2013 and June 2013 on the outbreak of avian influenza in China, we used vector autoregression to test the research model. We find a cyclical relationship between microblog volume and the intensity of negative emotions (fear in particular, a subcategory of negative emotions). Microblog volume positively contributes to positive emotions. While the intensity of negative emotions, and that of positive emotions is autocorrelated, respectively, surprisingly our results suggest that negative emotion intensity positively affects positive emotion intensity. We further rely on impulse response functions to illustrate how the impacts of a variable on another change over time, and generalized forecast error variance decomposition to understand the importance of each variable contributing to the others. Theoretical and practical implications of the study are discussed.