A study on an emotion model for prosody control and dialog management in speech communication

语音交流中韵律控制和对话管理的情感模型研究

• 批准号: 17500079
• 负责人: OHNO Sumio
• 金额: $ 1.98万
• 依托单位: Tokyo University of Technology
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (C)
• 财政年份: 2005
• 资助国家: 日本
• 起止时间: 2005 至 2006
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-17500079/
• 关键词: spoken utterance; emotion; spoken language model; prosody; mind model; 音声情報処理; 感情表現; 基本周波数パターン

In this scientific research project, it was achieved that a conversational system can process the emotion, and the object was 1) concerning the spoken expression of the emotional utterances and 2) concerning the modeling emotions in a dialog management. The following results were obtained in this project.1) Emotional expression of synthetic speechNot only the kind of emotions but also the levels of their strength were our research targets. Four emotions, i.e., "Joy", "Sadness", "Anger", and "Fear" were taken up as a kind of feelings, and prosodic features of the emotional utterances were examined by collecting and analyzing it for synthesizing expressive speech with controlling the level of the emotion. The controlling rule war formulated on the basis of a linear modeling of obtained prosodic parameters. The evaluation experiment was conducted by a synthetic speech. As a result, emotional strength control can be realized with a limitation of the kinds of emotions. A relatively good performance was obtained for "sadness" and "fear" in case of controlling the pitch features.2) Modeling of emotions in dialog managementWhen the processing of the expression of emotion is taken to the conversation between human and machine, advanced communications function is achieved by guessing other's emotions. It proposed an engineering model of the mind. The knowledge representation in the model of the mind was defined from the viewpoint of "Own inner environment", "Own inner environment from others" and "Own external environment from others", and emotions located it with one parameter of an inner environment. Moreover, the guess method by the inference-by-synthesis technique was designed as a processing technique for the others recognition in the model of the mind.

在这个科学研究项目中，已经实现了对话系统可以处理情绪，而对象是1）关于情绪发言的口语，以及2）关于对话框管理中的建模情绪。在本项目中获得了以下结果。1）合成语音的情绪表达仅是情绪的种类，而其力量的水平也是我们的研究目标。四种情绪，即“欢乐”，“悲伤”，“愤怒”和“恐惧”是一种感受，通过收集和分析以控制情感水平来综合表达语音，从而检查了情感话语的韵律特征。根据获得的韵律参数的线性建模制定的控制规则战争。评估实验是通过合成语音进行的。结果，可以通过限制各种情绪来实现情感力量控制。在控制音高特征的情况下，获得了相对较好的表现。2）对话管理中的情绪建模，当时情绪表达的处理被带到人与机器之间的对话中，通过猜测他人的情绪来实现高级通信功能。它提出了一种思维的工程模型。思想模型中的知识表示是从“自身内在环境”，“与他人的内部环境”和“来自他人的自己的外部环境”的角度定义的，而情绪则以内在环境的一个参数定位。此外，通过逐一推理技术的猜测方法被设计为对其他人在心灵模型中识别的处理技术。

项目成果

生成過程モデルに基づく感情表現におけるFOパターン制御規則の導出と合成音声による評価

基于生成过程模型的情感表达FO模式控制规则推导和合成语音评估

• 发表时间: 2006
• 期刊: 電子情報通信学会論文誌D J89-D・8
• 作者: 榊 重信;伊藤 慶明;石亀 昌明;小嶋 和徳;河津 宏美
• 通讯作者: 河津 宏美

癒し系ロボットPDDINの分析および福祉と認知リハビリテーションへの応用に関する研究

康复机器人PDDIN分析及其在福利和认知康复中的应用研究

• 发表时间: 2007
• 期刊: 電子情報通信学会技術研究報告 TL2006-66(WIT2006-98)
• 作者: K.Sato;Y.Hamada;M.Morimoto and K.Fujii;河津宏美;小澤朋之
• 通讯作者: 小澤朋之

「怒り」の感情表現とその言語表現-音響的特徴

“愤怒”的情感表达及其语言表达——声学特征

• 发表时间: 2006
• 期刊: 言語処理学会第12回年次大会ワークショップ「感情・評価・言語と態度」論文集
• 作者: 吉田;拓真;伊藤;慶明;石亀;昌明;小嶋;和徳;有本泰子
• 通讯作者: 有本泰子

韻律生成過程モデルに基づく4種の感情表現の特徴の分析

基于韵律生成过程模型的四类情感表达特征分析

• 发表时间: 2005
• 期刊: 日本音響学会2005年秋季研究発表会講演論文集
• 作者: 鈴木;聡;石亀;昌明;伊藤;慶明;小嶋;和徳;長島大介
• 通讯作者: 長島大介

Analysis of the relationship between F0 contour parameters and perceived degree of emotion in Japanese utterances

日语言语中F0轮廓参数与情感感知程度的关系分析

• 发表时间: 2005
• 期刊: Proceedings of the 10^<th> International Conference on Speech and Computer 2
• 作者: 土井健司;井上正博;田坂未来;平島大志郎;勅使河原可海;Hiromi Kawatsu
• 通讯作者: Hiromi Kawatsu