面向情感语音识别的建模方法研究

情感是语音识别研究中一个不可避免的问题,不同的情感对于语音有着不同的影响,这种影响使得中性语音识别系统在实际应用中的识别效果大打折扣。对于类似的影响通常的解决方法有寻找鲁棒特征,特征归一化以度模型调整训练等。本文通过自适应方法,使用少量情感数据,在中性语音模型的基础上自适应得到新的情感语音模型。实验证明,新模型对于情感语音有着更好的整体识别率。     

情感语音合成综述

情感语音合成作为一个新兴的语音合成方向,糅合生理学、心理学、语言学和信息科学等各学科知识,可以应用于文本阅读、信息查询发布和计算机辅助教学等领域,能够很好地将语音的口语分析、情感分析与计算机技术有机融合,为实现以人为本,具有个性化特征的语音合成系统奠定基础。目前的情感语音合成工作可分为基于规则合成和基于波形拼接合成两类。情感语音合成研究分为情感分析和语音合成两个部分。其中．情感分析的主要工作是收集不同情感的语音数据、提取声学特征,分析声学特征与情感联系;语音合成的主要工作是建立情感转换模型,利用情感转换模型实现合成。     

Experiencing the Affective Diary

A diary is generally considered to be a book in which one keeps a regular record of events and experiences that have some personal significance. As such, it provides a useful means to privately express inner thoughts or to reflect on daily experiences, helping in either case to put them in perspective. Taking conventional diary keeping as our starting point, we have designed and built a digital diary, named Affective Diary, with which users can scribble their notes, but that also allows for bodily memorabilia to be recorded from body sensors and mobile media to be collected from users’ mobile phones. A premise that underlies the presented work is one that views our bodily experiences as integral to how we come to interpret and thus make sense of the world. We present our investigations into this design space in three related lines of inquiry: (1) a theoretical grounding for affect and bodily experiences; (2) a user-centred design process, arriving at the Affective Diary system; and (3) an exploratory end-user study of the Affective Diary with 4 users during several weeks of use. Through these three inquiries, our overall aim has been to explore the potential of a system that interleaves the physical and cultural features of our embodied experiences and to further examine what media-specific qualities such a design might incorporate. Concerning the media-specific qualities, the key appears to be to find a suitable balance where a system does not dictate what should be interpreted and, at the same time, lends itself to enabling the user to participate in the interpretive act. In the exploratory end-user study users, for the most part, were able to identify with the body memorabilia and together with the mobile data, it enabled them to remember and reflect on their past. Two of our subjects went even further and found patterns in their own bodily reactions that caused them to learn something about themselves and even attempt to alter their own behaviours.

基于层叠模型细粒度情感要素抽取及倾向分析

针对商品评论中的细粒度情感要素抽取问题,提出基于条件随机场模型( CRFs)和支持向量机( SVM)的层叠模型。针对情感对象与情感词的识别,将评论的句法信息、语义信息等引入CRFs模型,进一步提高CRFs特征模板的鲁棒性。在SVM模型中,引入情感对象和情感词的深层词义及情感词的基本情感倾向等特征,改进传统的词包模型,对掖情感对象,情感词业词对进行细粒度的情感分类判断,从而获得商品评论中的情感关键信息：(情感对象,情感词,情感倾向性)三元组。实验表明,文中的CRFs和SVM层叠模型可提高情感要素抽取与情感分类判断的准确性。     

The disenchantment of affect

In computing design, experience is often broken down, compartmentalized, and engineered: a process that often disenchants the original experience. In this paper, we demonstrate the possibility to design for experience, not by formalizing and rationalizing it, but instead by supporting open-ended engagement and appropriation. We illustrate this approach through Affector, a case study in affective computing, in which we focus on user interpretation and construction of emotional experience over its computational modeling. We derive design and evaluation strategies for enchantment that focus on supporting the ongoing construction and interpretation of experience by human participants over the course of interaction. We suggest that enchanting experiences may be designed only by approaching enchantment obliquely: not by engineering it in, but by providing opportunities where it may emerge.     

Evaluating the effect of interactions between appearance-related product designs and facial characteristics on social affectivity

For products that can improve the appearance of the user, such as facial accessories, both the characteristics of the product user and design features must be considered in design evaluation. This paper proposes an experimental evaluation scheme that investigates the interactions between the design features of 3D eyeglasses frames and user facial characteristics. Face models of users containing both geometric and image data were constructed using 3D scanning. A face deformation method was developed to manipulate individual facial features without changing the other features on the face models. In the evaluation scheme, participants judged synthetic faces, which had varied eye distances and orientations and were wearing factorized eyeglasses frames, according to three affective measures related to the personality attributes of confidence, friendliness, and attractiveness. The experimental results show that changing certain design features influences the impressions of the face models with varied facial characteristics. The proposed scheme facilitates designing products that strengthen the impression of specific personality traits by accommodating individual differences in facial features.Relevance to industryThe evaluation scheme proposed in this paper facilitates designing products that strengthen the impression of specific personality traits by accommodating individual differences in facial features. By the scheme, companies can create products and services that satisfy individual customer requirements of personalized design.     

基于PAD情感模型的可训练语音合成研究

情感语音合成是情感计算和语音信号处理研究的热点之一,进行准确的语音情感分析是合成高质量情感语音的前提.文中采用PAD情感模型作为情感分析量化模型,对情感语料库中的语音进行情感分析和聚类,获得各情感PAD参数模型.由HMM语音合成系统合成的情感语音,通过PAD模型进行参数修正,使得合成语音的情感参数更加准确,从而提高情感语音合成的质量.实验表明该方法能较好地提高合成语音的自然度和情感清晰度,在同性别不同说话人中也能达到较好的性能.     

情感计算数学模型的研究初探

针对计算机如何进行情感计算,提出一种情感空间的概率模型并对其进行了计算机仿真。通过构造状态的概率转移矩阵,得到每个情感状态的概率分布,从而计算出情感的熵值。情感的熵值,表达出所构造的情感的细腻程度。通过计算机仿真,验证了情感模型是符合人类情感规律的——不确定性同时又具有统计规律。最后通过不同参数的仿真,说明此模型可以产生不同的情感活动,为情感机器人数学模型的建立与情感决策支持系统提供了一种新的方法。     

情感建模研究进展

情感建模在和谐人机交互及情感机器人方向有着广泛应用,是情感计算及人工心理理论研究的主要内容．本文对情感建模研究现状及其相关应用作了较为详细的分析与综述,指出了情感建模目前所面临的问题及难点．     

Application of Evolutionary Neural Networks on Optimization Design of Mobile Phone Based on User's Emotional Needs

Taking users’ emotional needs into consideration, this research aims to propose a new method to present product design features exactly and completely. On the basis of genetic algorithm integrated with back‐propagation (BP) neural networks, taking the mobile phone as research object, an optimization design algorithm was finally designed. First, the continuous and discrete design variables that describe mobile phones were screened with methods of dimensions, coordinate label, and morphological analysis. Forty three‐dimensional (3D) mobile phone models were designed by using 3D design software PROE. Accordingly, 12 representative mobile phones were selected through multidimensional scaling analysis and cluster analysis. Fourteen pairwise Kansei image words were obtained by collecting, screening, surveys, and statistical analysis method. Second, a BP neural networks model between design variables and user preference along with Kansei image words was established and verified with questionnaire survey data. Finally, the optimization design model for mobile phones was established considering design requirements and users’ emotional needs. A genetic algorithm integrated with BP neural networks was used to optimize mobile phone design. The results show that the optimization scheme is superior to others, and this paper will provide design suggestion for mobile phone designers.     

JD‐C Model to Explain Burnout in Frontline Workers: The Useful Contribution of Emotional Demands

Using the Job Demands‐Control (JD‐C) model as the theoretical framework, this study investigated the relationships among burnout, job demands, and autonomy. With a sample of 802 employees from a Portuguese bank, we demonstrated the importance of taking into account emotional job demands when studying the burnout of service providers. Thereby, the unique explanatory power of each emotional demand on burnout was tested with regression analysis, after controlling for the original demands and autonomy variables from the JD‐C model along with demographic variables. The results confirmed the relevance of the study model in explaining burnout and indicated that emotional dissonance was associated with employee burnout, beyond quantitative demands and autonomy. As expected, hierarchical regression analysis provided evidence for the main effects of quantitative demands, emotional dissonance, and autonomy on burnout. These findings have several implications for designing jobs involving interactions with clients. © 2011 Wiley Periodicals, Inc.     

Emotional facial expression model building

Human face plays a crucial role in interpersonal communication. If we synthesize vivid expressional face in cyberspace, we could make the interaction between computer and human more natural and friendly. In this paper, we present a simple methodology for mimicking realistic face by manipulating emotional states. Compared with traditional methods of facial expression synthesis, our approach takes three advantages at the same time. They are (1) generating facial expressions under quantitative control of emotional states, (2) rendering shape and illumination changes on face simultaneously and (3) synthesizing expressional face for any new person by only utilizing a neutral face image. We have discussed the implementation method in the paper and demonstrated the effects of our approach by using a series of interesting experiments, such as predicting unseen expressions for an unfamiliar person, simulating one’s facial expressions with someone else’s style, extracting pure emotional expressions from the admixtures.     

多媒体要素与记忆规律及情感激励作用关系初探

文章探讨了多媒体元素的交互式特征的重要地位,对多媒体的多感官刺激与记忆规律之间的深层科学影响关系进行了研究,揭示了语文学科中独特的情感激励过程,对于提高多媒体教学效果、指导多媒体课件设计、强化多媒体系统功能等方面都有非常现实的指导意义。     

The Relationship between Coworker Incivility,Emotional Exhaustion,and Organizational Outcomes: The Mediating Role of Emotional Exhaustion

The aim of this research is to investigate the relationship between coworker incivility, emotional exhaustion, and organizational outcomes measured by job satisfaction, job performance, and turnover intention. Working with a sample of 286 retail bank employees in South Korea, structural equation modeling is employed to test four hypotheses drawing on conservation of resources (COR) theory and affective events theory (AET). According to the analyses, while employee incivility positively affects emotional exhaustion, emotional exhaustion has a negative effect on job satisfaction and job performance. In addition, emotional exhaustion has a positive impact on turnover intention among organizational employees. These results imply that to better understand the relationship between coworker incivility and organizational outcomes, it is necessary to consider emotional exhaustion as an important mediating variable. The theoretical and practical implications of this study are discussed, together with its limitations and future research directions.     

基于马尔可夫链的情感计算建模方法

定义了情感的两种状态及其两个基本的变化转移过程,并应用马尔可夫链构造了一个情感概率空间,建立模拟情感变化的情感模型,给出了情感能量、情感强度和情感熵等概念,用以描述情感特征与情感状态。通过Matlab的仿真计算,验证此模型可较好地模拟情感状态自发转移的动态过程,可用于情感机器人的情感模拟计算。为情感计算和情感自动生成理论研究提供了一种新途径。     

学龄前儿童交互玩具情感体验设计研究

文章以情感化体验在产品设计中的作用为启示,对儿童交互类玩具产品进行了创新性研究。分析了儿童心理特征及交互类玩具的市场需求,论述了设计中情感法则对日常生活中的儿童类产品的作用与价值。在此基础上,提出了儿童交互类产品的创新性策略以及情感化互动的重要性与合理性,进而提出针对学龄前儿童玩具设计的概念模型。     

情感等级BDI主体模型研究

信念、愿望和意图(BDI)模型是近年来影响最为深远的主体技术之一。文中把命题动态逻辑和无穷值的ukasiewicz逻辑进行融合后对情感等级BDI主体模型进行了形式化。为通过信念度、愿望度、意图度、害怕度、焦虑度和自信度对不确定性行为进行表示和推理,把相应的公理添加到ukasiewicz逻辑中。文中的情感等级BDI主体模型的行为是通过添加具体条件的每种背景的不同测度来决定,清晰地表示主体的心理状态和情感状态的不确定性。文中对情感等级BDI模型进行公理化,并说明它们对主体行为的影响。此模型可较轻易地向包括其它心理状态和情感状态的主体进行推广。文中在给出情感等级BDI模型的语言、语义及公理和演绎规则后,证明此逻辑系统的可靠性和完全性。随后给出情感等级BDI主体模型的不同背景之间的相互关系,并对该主体的买房行动进行实例分析。本研究立足于不确定性的表示和推理,旨在为分布式人工智能提供形式支持。     

Emotional design in multimedia learning: Differentiation on relevant design features and their effects on emotions and learning

Previous research into multimedia learning has mainly focused on cognitive factors to investigate different instructional conditions and design principles. Emotional factors have so far been widely neglected. However, recent studies showed that the emotional design of multimedia learning material can evoke positive emotions in learners that in turn facilitate the learning process. Following this lead, our study aims to further explore the potential of an emotional design. We seek to differentiate the current findings by systematically deducing emotionally relevant design features and also taking into account negative emotional states. In order to deduce relevant design features, we adopt concepts from web design. German college students (N = 334) were assigned to one of nine conditions, created by two design factors (classical vs. expressive aesthetics), each with two levels (high vs. low) and a usability factor (high vs. low usability) as well as a control group (no color/gray scale). Unexpectedly, objective differences in aesthetics or usability did not affect learners’ emotional states. However, the perceived aesthetics and usability positively affected the emotional states of the learners. Learners’ emotional states had a minor impact on learning outcomes but a larger impact on learners’ intrinsic motivation, including the motivation to continue working with the material.     

人居互动中室内空间形态的情感化表达

人是当今环境的主角,随着现代人居空间设计的思路逐渐向关怀人文尺度转变,文章通过对室内空间形态和人文意识转换过程的研究,将重点放在人居互动的情感表达方面,人和空间通过不同的认知、情感、互动体验实现有意义的对话关系,通过人性化、智能化、功能化几个方面来分析人居互动中是如何达到满足人们行为需求的设计,最终做出具有丰富情感关怀的设计。     

浅议富媒体交互广告界面设计中的情感体验与感官体验

通过对富媒体广告实例的调查分析,发现大部分富媒体广告只是单纯的增加画面的大小与信息的数量,而忽略了基于富媒体技术所应该具有的交互性,本文提出富媒体广告需要结合用户体验中的感官体验和情感体验增加交互界面设计,并在此基础上提出富媒体广告界面设计应遵循相关性、直观性、简约性等原则,满足用户体验的需求,深化互动层次,才能提升广告的宣传效应。