Synergistic Functional Spectrum Analysis: A Framework for Exploring the Multifunctional Interplay Among Multimodal Nonverbal Behaviours in Conversations

IF 9.8 2区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE IEEE Transactions on Affective Computing Pub Date : 2024-11-04 DOI:10.1109/TAFFC.2024.3491097
Mai Imamura;Ayane Tashiro;Shiro Kumano;Kazuhiro Otsuka
{"title":"Synergistic Functional Spectrum Analysis: A Framework for Exploring the Multifunctional Interplay Among Multimodal Nonverbal Behaviours in Conversations","authors":"Mai Imamura;Ayane Tashiro;Shiro Kumano;Kazuhiro Otsuka","doi":"10.1109/TAFFC.2024.3491097","DOIUrl":null,"url":null,"abstract":"A novel framework named the <italic>synergistic functional spectrum analysis</i> (sFSA) is proposed to explore the multifunctional interplay among multimodal nonverbal behaviours in human conversations. This study aims to reveal how multimodal nonverbal behaviours cooperatively perform communicative functions in conversations. To capture the intrinsic nature of nonverbal expressions, functional multiplicity, and interpretational ambiguity, e.g., a single head nod could imply listening, agreeing, or both, a novel concept named the <italic>functional spectrum</i>, which is defined as the distribution of perceptual intensities of multiple functions by multiple observers, is introduced in the sFSA. Based on this concept, this paper presents <italic>functional spectrum corpora</i>, which target 44 facial expression and 32 head movement functions. Then, spectrum decomposition is conducted to reduce the multimodal functional spectrum to a <italic>synergetic functional spectrum</i> in a lower dimension <italic>functional space</i> that is spanned by <italic>functional basis</i> vectors representing primary and distinctive functionalities across multiple modalities. To that end, we propose a semiorthogonal nonnegative matrix factorization (SO-NMF) method, which assumes the additivity of multiple functions and aims to balance the distinctiveness and expressiveness of the factorization. The results confirm that some primary functional bases can be identified, which can be interpreted as the listener’s backchannel, thinking, and affirmative response functions, and the speaker’s thinking and addressing functions, and their positive emotion functions. In addition, regression models based on convolutional neural networks (CNNs) are presented to estimate the <italic>synergistic functional spectrum</i> from the head poses and facial action units measured from conversation data. The results of these analyses and experiments confirm the potential of the sFSA and may lead to future extensions.","PeriodicalId":13131,"journal":{"name":"IEEE Transactions on Affective Computing","volume":"16 2","pages":"1056-1073"},"PeriodicalIF":9.8000,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Affective Computing","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10742505/","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

A novel framework named the synergistic functional spectrum analysis (sFSA) is proposed to explore the multifunctional interplay among multimodal nonverbal behaviours in human conversations. This study aims to reveal how multimodal nonverbal behaviours cooperatively perform communicative functions in conversations. To capture the intrinsic nature of nonverbal expressions, functional multiplicity, and interpretational ambiguity, e.g., a single head nod could imply listening, agreeing, or both, a novel concept named the functional spectrum, which is defined as the distribution of perceptual intensities of multiple functions by multiple observers, is introduced in the sFSA. Based on this concept, this paper presents functional spectrum corpora, which target 44 facial expression and 32 head movement functions. Then, spectrum decomposition is conducted to reduce the multimodal functional spectrum to a synergetic functional spectrum in a lower dimension functional space that is spanned by functional basis vectors representing primary and distinctive functionalities across multiple modalities. To that end, we propose a semiorthogonal nonnegative matrix factorization (SO-NMF) method, which assumes the additivity of multiple functions and aims to balance the distinctiveness and expressiveness of the factorization. The results confirm that some primary functional bases can be identified, which can be interpreted as the listener’s backchannel, thinking, and affirmative response functions, and the speaker’s thinking and addressing functions, and their positive emotion functions. In addition, regression models based on convolutional neural networks (CNNs) are presented to estimate the synergistic functional spectrum from the head poses and facial action units measured from conversation data. The results of these analyses and experiments confirm the potential of the sFSA and may lead to future extensions.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
协同功能谱分析:探索对话中多模态非语言行为之间多功能相互作用的框架
本文提出了一个新的框架,即协同功能谱分析(sFSA),以探讨人类会话中多模态非语言行为之间的多功能相互作用。本研究旨在揭示多模态非语言行为在会话中如何协同执行交际功能。为了捕捉非语言表达的内在本质、功能多样性和解释模糊性,例如,一个点头可能意味着倾听、同意或两者兼有,sFSA引入了一个名为功能谱的新概念,它被定义为多个观察者对多种功能的感知强度的分布。基于这一概念,本文提出了针对44种面部表情和32种头部运动功能的功能谱语料库。然后,对多模态功能谱进行谱分解,将多模态功能谱降为由代表多模态主要功能和独特功能的功能基向量所组成的低维功能空间中的协同功能谱。为此,我们提出了一种半正交非负矩阵分解(SO-NMF)方法,该方法假设了多个函数的可加性,旨在平衡分解的独特性和表达性。研究结果表明,言语交际具有一定的基本功能基础,即听者的反向通道功能、思考功能和肯定回应功能,以及说话者的思考功能和寻址功能及其积极情绪功能。此外,提出了基于卷积神经网络(cnn)的回归模型,从会话数据中测量的头部姿势和面部动作单元估计协同功能谱。这些分析和实验的结果证实了sFSA的潜力,并可能导致未来的扩展。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
IEEE Transactions on Affective Computing
IEEE Transactions on Affective Computing COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE-COMPUTER SCIENCE, CYBERNETICS
CiteScore
15.00
自引率
6.20%
发文量
174
期刊介绍: The IEEE Transactions on Affective Computing is an international and interdisciplinary journal. Its primary goal is to share research findings on the development of systems capable of recognizing, interpreting, and simulating human emotions and related affective phenomena. The journal publishes original research on the underlying principles and theories that explain how and why affective factors shape human-technology interactions. It also focuses on how techniques for sensing and simulating affect can enhance our understanding of human emotions and processes. Additionally, the journal explores the design, implementation, and evaluation of systems that prioritize the consideration of affect in their usability. We also welcome surveys of existing work that provide new perspectives on the historical and future directions of this field.
期刊最新文献
EmoSENSE: Modeling Sentiment-Semantic Knowledge with Hierarchical Reinforcement Learning for Emotional Image Generation Emo-DiT: Emotional Speech Synthesis With a Diffusion Model Approach to Enhance Naturalness and Emotional Expressiveness InterARM: Interpretable Affective Reasoning Model for Multimodal Sarcasm Detection Exploring canine emotions: A transfer learning and 3DCNN-based study for small databases Fine-grained EEG emotion recognition using lite residual convolution-based transformer neural network
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1