A blog emotion corpus for emotional expression analysis in Chinese

Weblogs are increasingly popular modes of communication and they are frequently used as mediums for emotional expression in the ever changing online world. This work uses blogs as object and data source for Chinese emotional expression analysis. First, a textual emotional expression space model is described, and based on this model, a relatively fine-grained annotation scheme is proposed for manual annotation of an emotion corpus. In document and paragraph levels, emotion category, emotion intensity, topic word and topic sentence are annotated. In sentence level, emotion category, emotion intensity, emotional keyword and phrase, degree word, negative word, conjunction, rhetoric, punctuation, objective or subjective, and emotion polarity are annotated. Then, using this corpus, we explore these linguistic expressions that indicate emotion in Chinese, and present a detailed data analysis on them, involving mixed emotions, independent emotion, emotion transfer, and analysis on words and rhetorics for emotional expression.     

面向汉语统计参数语音合成的标注生成方法

针对汉语统计参数语音合成中的上下文相关标注生成,设计了声韵母层、音节层、词层、韵律词层、韵律短语层和语句层6层上下文相关的标注格式。对输入的中文语句进行文本规范并利用语法分析获得语句的结构和分词信息;通过字音转换获得每个汉字的声韵母及声调;利用TBL（Transformation-Based error driven Learning）算法预测输入文本的韵律词边界和韵律短语边界。在此基础上,获得输入文本中每个汉字的声韵母信息及其上下文结构信息,从而产生统计参数语音合成所需的上下文相关标注。设计了一个以声韵母为合成基元的普通话的基于隐Markov模型（HMM）的统计参数语音合成系统,通过主、客观实验评测了不同标注信息对合成语音音质的影响,结果表明,上下文相关的标注信息越丰富,合成语音的音质越好。     

基于PCA和SVM的普通话语音情感识别

在语音情感识别中,情感特征的选取与抽取是重要环节。目前,还没有非常有效的语音情感特征被提出。因此,在包含6种情感的普通话情感语料库中,根据普通话不同于西方语种的特点,选取了一些有效的情感特征,包含Mel频率倒谱系数、基频、短时能量、短时平均过零率和第一共振峰等,进行提取并计算得到不同的统计量;接着采用主成分分析(PCA)进行抽取;最后利用基于支持向量机(SVM)的语音情感识别系统进行分类。实验结果表明, 与其他一些重要的研究结果相比,该方法得到了较高的平均情感识别率, 且情感特征的选取、抽取及建模是合理、有效的。     

手语到情感语音的转换

为了解决语言障碍者与健康人之间的交流障碍问题,提出了一种基于神经网络的手语到情感语音转换方法。首先,建立了手势语料库、人脸表情语料库和情感语音语料库;然后利用深度卷积神经网络实现手势识别和人脸表情识别,并以普通话声韵母为合成单元,训练基于说话人自适应的深度神经网络情感语音声学模型和基于说话人自适应的混合长短时记忆网络情感语音声学模型;最后将手势语义的上下文相关标注和人脸表情对应的情感标签输入情感语音合成模型,合成出对应的情感语音。实验结果表明,该方法手势识别率和人脸表情识别率分别达到了95.86%和92.42%,合成的情感语音EMOS得分为4.15,合成的情感语音具有较高的情感表达程度,可用于语言障碍者与健康人之间正常交流。     

融合词义信息的中文短语句法分析

针对目前融合词义信息的短语句法分析过程中,多义词词义消歧较差的问题,提出一种基于词性消歧的中文短语句法分析方法。首先构建具有词性信息的同义词字典;然后对训练集和测试集中的词语进行词义替换,利用多义词的词性区分其不同的词义。在宾州中文树库(CTB)的实验结果表明,正确率为80.30%,召回率为78.12%,F值为79.19%。相对于没有进行词性消歧的系统,该方法有效提高了短语句法分析的性能。     

加入调型信息的汉语孤立词识别研究

汉语是一种有调语言,因此在汉语语音识别中,调型信息起着非常关键的作用。在现有的隐马尔可夫模型(Hidden Markov Model)框架下,如何有效地利用调型信息是有待研究的问题。现有的汉语语音识别系统中主要采用两种方式来使用调型信息 一种是基于Embedded Tone Model,即将调型特征向量与声学特征向量组成一个流去训练模型;一种是Explicit Tone Model,即将调型信息单独建模,再利用此模型优化原有的解码网络。该文将两种方法统一起来,首先利用Embedded Tone Model采用双流而非单流建模得到Nbest备选,再利用Explicit Tone Model对调进行左相关建模并对Nbest得分重新修正以得到识别结果,从而获得性能提升。与传统的无调模型相比,该文方法的识别率的平均绝对提升超过了3.0%,在第三测试集上的绝对提升达到了5.36%。     

汉语短语识别方法研究

在自然语言处理中,短语在汉语分析中占有举足轻重的地位。短语作为汉语句子中的一个基本组成单位,在整个汉语句子的句法分析与语义分析中具有特别重要的意义。为了提高汉语分析的质量,文中在借鉴他人算法的基础上,提出了一种规则和统计相结合的短语识别方法。首先利用词或词语之间的互信息进行短语边界的预测,然后根据词语的词汇和词类信息进行边界调整,最后进行括号匹配和短语标注。实验结果表明：该方法提高了短语的识别率和准确率,提高了汉语分析的质量。     

Expressing reactive emotion based on multimodal emotion recognition for natural conversation in human–robot interaction*

Human–human interaction consists of various nonverbal behaviors that are often emotion-related. To establish rapport, it is essential that the listener respond to reactive emotion in a way that makes sense given the speaker's emotional state. However, human–robot interactions generally fail in this regard because most spoken dialogue systems play only a question-answer role. Aiming for natural conversation, we examine an emotion processing module that consists of a user emotion recognition function and a reactive emotion expression function for a spoken dialogue system to improve human–robot interaction. For the emotion recognition function, we propose a method that combines valence from prosody and sentiment from text by decision-level fusion, which considerably improves the performance. Moreover, this method reduces fatal recognition errors, thereby improving the user experience. For the reactive emotion expression function, the system's emotion is divided into emotion category and emotion level, which are predicted using the parameters estimated by the recognition function on the basis of distributions inferred from human–human dialogue data. As a result, the emotion processing module can recognize the user's emotion from his/her speech, and expresses a reactive emotion that matches. Evaluation with ten participants demonstrated that the system enhanced by this module is effective to conduct natural conversation.     

Emotion recognition and adaptation in spoken dialogue systems

The involvement of emotional states in intelligent spoken human-computer interfaces has evolved to a recent field of research. In this article we describe the enhancements and optimizations of a speech-based emotion recognizer jointly operating with automatic speech recognition. We argue that the knowledge about the textual content of an utterance can improve the recognition of the emotional content. Having outlined the experimental setup we present results and demonstrate the capability of a post-processing algorithm combining multiple speech-emotion recognizers. For the dialogue management we propose a stochastic approach comprising a dialogue model and an emotional model interfering with each other in a combined dialogue-emotion model. These models are trained from dialogue corpora and being assigned different weighting factors they determine the course of the dialogue.     

Paraphrastic language models

Natural languages are known for their expressive richness. Many sentences can be used to represent the same underlying meaning. Only modelling the observed surface word sequence can result in poor context coverage and generalization, for example, when using n-gram language models (LMs). This paper proposes a novel form of language model, the paraphrastic LM, that addresses these issues. A phrase level paraphrase model statistically learned from standard text data with no semantic annotation is used to generate multiple paraphrase variants. LM probabilities are then estimated by maximizing their marginal probability. Multi-level language models estimated at both the word level and the phrase level are combined. An efficient weighted finite state transducer (WFST) based paraphrase generation approach is also presented. Significant error rate reductions of 0.5–0.6% absolute were obtained over the baseline n-gram LMs on two state-of-the-art recognition tasks for English conversational telephone speech and Mandarin Chinese broadcast speech using a paraphrastic multi-level LM modelling both word and phrase sequences. When it is further combined with word and phrase level feed-forward neural network LMs, a significant error rate reduction of 0.9% absolute (9% relative) and 0.5% absolute (5% relative) were obtained over the baseline n-gram and neural network LMs respectively.     

基于改进的排序式选举算法的语音情感融合识别

根据情感的连续空间模型,提出一种改进的排序式选举算法,实现多个情感分类器的融合,取得了很好的情感识别效果。首先以隐马尔可夫模型（HMM）和人工神经网络（ANN）为基础,设计了三种分类器;然后用改进的排序式选举算法,实现对三种分类器的融合。分别利用普通话情感语音库和德语情感语音库进行实验,结果表明,与几种传统融合算法相比,改进的排序式选举法能够取得更好的融合效果,其识别性能明显优于单分类器。该算法不仅简单,而且可移植性好,可用于其他任意多个情感分类器的融合。     

融合语音情感词局部特征的语音情感识别方法

为有效利用语音情感词局部特征,提出了一种融合情感词局部特征与语音语句全局特征的语音情感识别方法。该方法依赖于语音情感词典的声学特征库,提取出语音语句中是否包含情感词及情感词密度等局部特征,并与全局声学特征进行融合,再通过机器学习算法建模和识别语音情感。对比实验结果表明,融合语音情感词局部特征与全局特征的语音情感识别方法能取得更好的效果,局部特征的引入能有效提高语音情感识别准确率。     

利用三层条件随机场模型进行情感极性分类及强度分析

通过对商品评论进行基于方面的情感分析,可以得到某件商品各个方面的优劣情况。本文提出利用三层CRFs模型进行情感极性分类及强度分析。在CRFs模型中,融合了词、词性、语气词、程度词、方面和评价词的共现等特征。在情感句识别、情感极性分类和情感强度分析上得到的F1值分别为86.3%、77.2%、70.7%,证明了：(1)分层CRFs模型在各个层次的任务中都能取得较好的结果;(2) 语气词、程度词、方面和评价词的共现特征在情感分类时是的有效性。     

基于OCC模型和贝叶斯网络的情绪句分类方法

情绪句分类是情绪分析研究领域的核心问题之一,旨在解决情绪句类别的自动判断问题。传统基于情绪认知模型(OCC模型)的情绪句分类方法大多依赖词典和规则,在文本信息缺失的情况下分类精度不高。文中提出基于OCC模型和贝叶斯网络的情绪句分类方法,通过分析OCC模型的情绪生成规则,提取情绪评估变量并结合情绪句中含有的表情符号特征构建情绪分类贝叶斯网络;通过概率推理,可以实现句子级文本的情绪分类,并减小句中信息缺失所带来的影响。与NLPCC2014中文微博情绪分析评测的子任务情绪句分类评测结果的对比表明,所提方法具有有效性。     

Modular neural-SVM scheme for speech emotion recognition using ANOVA feature selection method

The speech signal consists of linguistic information and also paralinguistic one such as emotion. The modern automatic speech recognition systems have achieved high performance in neutral style speech recognition, but they cannot maintain their high recognition rate for spontaneous speech. So, emotion recognition is an important step toward emotional speech recognition. The accuracy of an emotion recognition system is dependent on different factors such as the type and number of emotional states and selected features, and also the type of classifier. In this paper, a modular neural-support vector machine (SVM) classifier is proposed, and its performance in emotion recognition is compared to Gaussian mixture model, multi-layer perceptron neural network, and C5.0-based classifiers. The most efficient features are also selected by using the analysis of variations method. It is noted that the proposed modular scheme is achieved through a comparative study of different features and characteristics of an individual emotional state with the aim of improving the recognition performance. Empirical results show that even by discarding 22% of features, the average emotion recognition accuracy can be improved by 2.2%. Also, the proposed modular neural-SVM classifier improves the recognition accuracy at least by 8% as compared to the simulated monolithic classifiers.     

Survey on speech emotion recognition: Features, classification schemes, and databases

Recently, increasing attention has been directed to the study of the emotional content of speech signals, and hence, many systems have been proposed to identify the emotional content of a spoken utterance. This paper is a survey of speech emotion classification addressing three important aspects of the design of a speech emotion recognition system. The first one is the choice of suitable features for speech representation. The second issue is the design of an appropriate classification scheme and the third issue is the proper preparation of an emotional speech database for evaluating system performance. Conclusions about the performance and limitations of current speech emotion recognition systems are discussed in the last section of this survey. This section also suggests possible ways of improving speech emotion recognition systems.     

句对齐研究综述

神经机器翻译是目前机器翻译领域的主流方法,拥有足够数量的双语平行语料是训练出一个好的翻译模型的前提。双语句对齐技术作为一种从不同语言端单语语料中获取双语平行句对的技术,因此得到广泛的研究。该文首先简单介绍句对齐任务及其相应的评测标准,然后归纳总结前人在句对齐任务上的研究进展,以及句对齐任务的相关信息,并简单概括参加团队所提交的系统,最后对当前工作进行总结并展望未来的工作。     

一种基于脉冲耦合神经网络的语音情感识别新方法

针对汉语语音情感识别问题,提出了一种基于脉冲耦合神经网络(PCNN)的识别方法。该方法将语音转化为语谱图后输入到PCNN,得到输出图像的神经元点火序列及其熵序列作为语音情感的特征,利用其特征实现语音情感识别。实验结果表明,该方法可以有效地识别“高兴”与“平常”这两种不同的情感。该方法将PCNN引入到语音情感识别的应用研究中,开拓了语音和图像信号结合处理的新领域,同时对于PCNN的理论研究和实际应用具有重要的现实意义。     

Combining language models in the input interface of a spoken dialogue system

This paper presents a new technique to enhance the performance of the input interface of spoken dialogue systems based on a procedure that combines during speech recognition the advantages of using prompt-dependent language models with those of using a language model independent of the prompts generated by the dialogue system. The technique proposes to create a new speech recognizer, termed contextual speech recognizer, that uses a prompt-independent language model to allow recognizing any kind of sentence permitted in the application domain, and at the same time, uses contextual information (in the form of prompt-dependent language models) to take into account that some sentences are more likely to be uttered than others at a particular moment of the dialogue. The experiments show the technique allows enhancing clearly the performance of the input interface of a previously developed dialogue system based exclusively on prompt-dependent language models. But most important, in comparison with a standard speech recognizer that uses just one prompt-independent language model without contextual information, the proposed recognizer allows increasing the word accuracy and sentence understanding rates by 4.09% and 4.19% absolute, respectively. These scores are slightly better than those obtained using linear interpolation of the prompt-independent and prompt-dependent language models used in the experiments.