更改

'''情感计算''' '''Affective computing '''（也被称为人工情感智能或情感AI）是基于系统和设备的研究和开发来识别、理解、处理和模拟人的情感。这是一个融合'''计算机科学'''、'''心理学'''和'''认知科学'''的跨学科领域<ref name=TaoTan>{{cite conference |first=Jianhua |last=Tao |author2=Tieniu Tan |title=Affective Computing: A Review |book-title=Affective Computing and Intelligent Interaction |volume=[[LNCS]] 3784 |pages=981–995 |publisher=Springer |year=2005 |doi=10.1007/11573548 }}</ref>。虽然该领域的一些核心思想可以追溯到早期对情感<ref name=":0">{{cite journal |last=James |first=William |year=1884 |title=What Is Emotion |journal=Mind |volume=9 |issue=34 |pages=188–205 |doi=10.1093/mind/os-IX.34.188|url=https://zenodo.org/record/1431811 }} Cited by Tao and Tan.</ref> 的哲学研究，但计算机科学的现代分支研究起源于罗莎琳德·皮卡德1995年关于情感计算的论文<ref name=":1">[http://affect.media.mit.edu/pdfs/95.picard.pdf "Affective Computing"] MIT Technical Report #321 ([http://vismod.media.mit.edu/pub/tech-reports/TR-321-ABSTRACT.html Abstract]), 1995</ref>和她的由麻省理工出版社<ref name=":2">

'''情感计算''' '''Affective computing '''（也被称为人工情感智能或情感AI）是基于系统和设备的研究和开发来识别、理解、处理和模拟人的情感。这是一个融合'''计算机科学'''、'''心理学'''和'''认知科学'''的跨学科领域<ref name=TaoTan>{{cite conference |first=Jianhua |last=Tao |title=Affective Computing: A Review |book-title=Affective Computing and Intelligent Interaction |volume=LNCS 3784 |pages=981–995 |publisher=Springer |year=2005 |doi=10.1007/11573548 }}</ref>。虽然该领域的一些核心思想可以追溯到早期对情感<ref name=":0">{{cite journal |last=James |first=William |year=1884 |title=What Is Emotion |journal=Mind |volume=9 |issue=34 |pages=188–205 |doi=10.1093/mind/os-IX.34.188|url=https://zenodo.org/record/1431811 }} Cited by Tao and Tan.</ref> 的哲学研究，但计算机科学的现代分支研究起源于罗莎琳德·皮卡德1995年关于情感计算的论文<ref name=":1">[http://affect.media.mit.edu/pdfs/95.picard.pdf "Affective Computing"] MIT Technical Report #321 ([http://vismod.media.mit.edu/pub/tech-reports/TR-321-ABSTRACT.html Abstract]), 1995</ref>和她的由麻省理工出版社<ref name=":2">

{{cite web

{{cite web

  |url=http://ls12-www.cs.tu-dortmund.de//~fink/lectures/SS06/human-robot-interaction/Emotion-RecognitionAndSimulation.pdf  

  |url=http://ls12-www.cs.tu-dortmund.de//~fink/lectures/SS06/human-robot-interaction/Emotion-RecognitionAndSimulation.pdf  

  |date=April 2006

  |date=April 2006

  | title = Assistive Technology and Affective Mediation

  | title = Assistive Technology and Affective Mediation

  | journal = [[Human Technology]]

  | journal = Human Technology

  | volume = 2

  | volume = 2

  | issue = 1

  | issue = 1

=== 语音情感 ===

=== 语音情感 ===

[https://zh.wikipedia.org/zh-sg/%E8%87%AA%E4%B8%BB%E7%A5%9E%E7%BB%8F%E7%B3%BB%E7%BB%9F 自主神经系统]的各种变化可以间接地改变一个人的语言，情感技术可以利用这些信息来识别情绪。例如，在恐惧、愤怒或高兴的状态下发言变得快速、响亮、清晰，音调变得越来越高，音域越来越宽；而诸如疲倦、厌倦或悲伤等情绪往往会产生缓慢、低沉、含糊不清的语音<ref name=":8">Breazeal, C. and Aryananda, L. [http://web.media.mit.edu/~cynthiab/Papers/breazeal-aryananda-AutoRo02.pdf Recognition of affective communicative intent in robot-directed speech]. Autonomous Robots 12 1, 2002. pp. 83–104.</ref>。有些情绪更容易被计算识别，比如愤怒<ref name="Dellaert" /> 或赞同<ref name=":9">{{Cite book|last1=Roy|first1=D.|last2=Pentland|first2=A.|date=1996-10-01|title=Automatic spoken affect classification and analysis|journal=Proceedings of the Second International Conference on Automatic Face and Gesture Recognition|pages=363–367|doi=10.1109/AFGR.1996.557292|isbn=978-0-8186-7713-7|s2cid=23157273}}</ref>。

[https://zh.wikipedia.org/zh-sg/%E8%87%AA%E4%B8%BB%E7%A5%9E%E7%BB%8F%E7%B3%BB%E7%BB%9F 自主神经系统]的各种变化可以间接地改变一个人的语言，情感技术可以利用这些信息来识别情绪。例如，在恐惧、愤怒或高兴的状态下发言变得快速、响亮、清晰，音调变得越来越高，音域越来越宽；而诸如疲倦、厌倦或悲伤等情绪往往会产生缓慢、低沉、含糊不清的语音<ref name=":8">Breazeal, C. and Aryananda, L. [http://web.media.mit.edu/~cynthiab/Papers/breazeal-aryananda-AutoRo02.pdf Recognition of affective communicative intent in robot-directed speech]. Autonomous Robots 12 1, 2002. pp. 83–104.</ref>。有些情绪更容易被计算识别，比如愤怒<ref name="Dellaert" /> 或赞同<ref name=":9">{{Cite book|last1=Roy|first1=D.|last2=Pentland|first2=A.|date=1996-10-01|title=Automatic spoken affect classification and analysis|journal=Proceedings of the Second International Conference on Automatic Face and Gesture Recognition|pages=363–367|doi=10.1109/AFGR.1996.557292}}</ref>。

情感语音处理技术通过对语音特征的计算分析来识别用户的情感状态。通过模式识别技术<ref name="Dellaert">Dellaert, F., Polizin, t., and Waibel, A., Recognizing Emotion in Speech", In Proc. Of ICSLP 1996, Philadelphia, PA, pp.1970–1973, 1996</ref><ref name="Lee">Lee, C.M.; Narayanan, S.; Pieraccini, R., Recognition of Negative Emotion in the Human Speech Signals, Workshop on Auto. Speech Recognition and Understanding, Dec 2001</ref>

情感语音处理技术通过对语音特征的计算分析来识别用户的情感状态。通过模式识别技术<ref name="Dellaert">Dellaert, F., Polizin, t., and Waibel, A., Recognizing Emotion in Speech", In Proc. Of ICSLP 1996, Philadelphia, PA, pp.1970–1973, 1996</ref><ref name="Lee">Lee, C.M.; Narayanan, S.; Pieraccini, R., Recognition of Negative Emotion in the Human Speech Signals, Workshop on Auto. Speech Recognition and Understanding, Dec 2001</ref>

  | url-access = registration

  | url-access = registration

  | publisher = Univ. of Illinois Press

  | publisher = Univ. of Illinois Press

  | year = 1975

  | year = 1975

}}

}}

# 频率特性<ref name=":14">{{Cite book |doi=10.1109/ICCCI50826.2021.9402569|isbn=978-1-7281-5875-4|chapter=Non-linear frequency warping using constant-Q transformation for speech emotion recognition|title=2021 International Conference on Computer Communication and Informatics (ICCCI)|pages=1–4|year=2021|last1=Singh|first1=Premjeet|last2=Saha|first2=Goutam|last3=Sahidullah|first3=Md|arxiv=2102.04029}}</ref>

# 频率特性<ref name=":14">{{Cite book |doi=10.1109/ICCCI50826.2021.9402569|chapter=Non-linear frequency warping using constant-Q transformation for speech emotion recognition|title=2021 International Conference on Computer Communication and Informatics (ICCCI)|pages=1–4|year=2021|last1=Singh|first1=Premjeet|last2=Saha|first2=Goutam|last3=Sahidullah|first3=Md|arxiv=2102.04029}}</ref>

* 音调形状（Accent shape ）：受基础频率变化的影响。

* 音调形状（Accent shape ）：受基础频率变化的影响。

* 平均音调（Average pitch）：描述说话者相对于正常语言的音调高低。

* 平均音调（Average pitch）：描述说话者相对于正常语言的音调高低。

=== 面部情感检测 ===

=== 面部情感检测 ===

面部表情的检测和处理通过[[wikipedia:Optical_flow|'''光流''']]、'''隐马尔可夫模型'''、'''神经网络'''或'''主动外观模型'''等多种方法实现。可以组合或融合多种模态（多模态识别，例如面部表情和语音韵律<ref name="face-prosody">{{cite conference | url = http://www.image.ece.ntua.gr/php/savepaper.php?id=447 | first1 = G. | last1 = Caridakis | first2 = L. | last2 = Malatesta | first3 = L. | last3 = Kessous | first4 = N. | last4 = Amir | first5 = A. | last5 = Raouzaiou | first6 = K. | last6 = Karpouzis | title = Modeling naturalistic affective states via facial and vocal expressions recognition | conference = International Conference on Multimodal Interfaces (ICMI'06) | location = Banff, Alberta, Canada | date = November 2–4, 2006 }}</ref>、面部表情和手势<ref name="face-gesture">{{cite book | chapter-url = http://www.image.ece.ntua.gr/php/savepaper.php?id=334 | first1 = T. | last1 = Balomenos | first2 = A. | last2 = Raouzaiou | first3 = S. | last3 = Ioannou | first4 = A. | last4 = Drosopoulos | first5 = K. | last5 = Karpouzis | first6 = S. | last6 = Kollias | chapter = Emotion Analysis in Man-Machine Interaction Systems | editor1-first = Samy | editor1-last = Bengio | editor2-first = Herve | editor2-last = Bourlard | title = Machine Learning for Multimodal Interaction | series = [[Lecture Notes in Computer Science]] | volume = 3361| year = 2004 | pages = 318–328 | publisher = [[Springer-Verlag]] }}</ref>，或用于多模态数据和元数据分析的带有语音和文本的面部表情），以提供对受试者情绪的更可靠估计。Affectiva 是一家与情感计算直接相关的公司(由 Rosalind Picard 和 Rana El Kaliouby 共同创办) ，旨在研究面部情感检测的解决方案和软件。

面部表情的检测和处理通过[[wikipedia:Optical_flow|'''光流''']]、'''隐马尔可夫模型'''、'''神经网络'''或'''主动外观模型'''等多种方法实现。可以组合或融合多种模态（多模态识别，例如面部表情和语音韵律<ref name="face-prosody">{{cite conference | url = http://www.image.ece.ntua.gr/php/savepaper.php?id=447 | first1 = G. | last1 = Caridakis | first2 = L. | last2 = Malatesta | first3 = L. | last3 = Kessous | first4 = N. | last4 = Amir | first5 = A. | last5 = Raouzaiou | first6 = K. | last6 = Karpouzis | title = Modeling naturalistic affective states via facial and vocal expressions recognition | conference = International Conference on Multimodal Interfaces (ICMI'06) | location = Banff, Alberta, Canada | date = November 2–4, 2006 }}</ref>、面部表情和手势<ref name="face-gesture">{{cite book | chapter-url = http://www.image.ece.ntua.gr/php/savepaper.php?id=334 | first1 = T. | last1 = Balomenos | first2 = A. | last2 = Raouzaiou | first3 = S. | last3 = Ioannou | first4 = A. | last4 = Drosopoulos | first5 = K. | last5 = Karpouzis | first6 = S. | last6 = Kollias | chapter = Emotion Analysis in Man-Machine Interaction Systems | editor1-first = Samy | editor1-last = Bengio | editor2-first = Herve | editor2-last = Bourlard | title = Machine Learning for Multimodal Interaction | series = [[Lecture Notes in Computer Science]] | volume = 3361| year = 2004 | pages = 318–328 | publisher = Springer-Verlag }}</ref>，或用于多模态数据和元数据分析的带有语音和文本的面部表情），以提供对受试者情绪的更可靠估计。Affectiva 是一家与情感计算直接相关的公司(由 Rosalind Picard 和 Rana El Kaliouby 共同创办) ，旨在研究面部情感检测的解决方案和软件。

==== 面部表情数据库 ====

==== 面部表情数据库 ====

==== 情感分类 ====

==== 情感分类 ====

二十世纪六十年代末，保罗·埃克曼 (Paul Ekman) 在巴布亚新几内亚的法雷人部落（ Fore Tribesmen） 上进行跨文化研究，提出了一种观点，即情感所对应的面部表情不是由文化决定的，而是普遍存在的。因此，他认为面部表情是生物本能，能够可靠地分类。<ref name="Ekman, P. 1969"/>因此，他在 1972 年正式提出了六种基本情绪<ref name=":15">{{cite conference | last = Ekman | first =  Paul | author-link = Paul Ekman | year = 1972 | title = Universals and Cultural Differences in Facial Expression of Emotion | editor-first = J. | editor-last = Cole | conference = Nebraska Symposium on Motivation | location = Lincoln, Nebraska | publisher = University of Nebraska Press | pages = 207–283 }}</ref>：

二十世纪六十年代末，保罗·埃克曼 (Paul Ekman) 在巴布亚新几内亚的法雷人部落（ Fore Tribesmen） 上进行跨文化研究，提出了一种观点，即情感所对应的面部表情不是由文化决定的，而是普遍存在的。因此，他认为面部表情是生物本能，能够可靠地分类。<ref name="Ekman, P. 1969"/>因此，他在 1972 年正式提出了六种基本情绪<ref name=":15">{{cite conference | last = Ekman | first =  Paul | year = 1972 | title = Universals and Cultural Differences in Facial Expression of Emotion | editor-first = J. | editor-last = Cole | conference = Nebraska Symposium on Motivation | location = Lincoln, Nebraska | publisher = University of Nebraska Press | pages = 207–283 }}</ref>：

* 愤怒  

* 愤怒  

然而，在20世纪90年代，埃克曼扩展了他的基本情绪列表，包括一系列积极和消极的情绪，这些情绪并非都对应于面部肌肉。<ref>{{Cite book|last=Ekman |first=Paul |author-link=Paul Ekman |year=1999 |url=http://www.paulekman.com/wp-content/uploads/2009/02/Basic-Emotions.pdf |contribution=Basic Emotions |editor1-first=T |editor1-last=Dalgleish |editor2-first=M |editor2-last=Power |title=Handbook of Cognition and Emotion |place=Sussex, UK |publisher=John Wiley & Sons |url-status=dead |archive-url=https://web.archive.org/web/20101228085345/http://www.paulekman.com/wp-content/uploads/2009/02/Basic-Emotions.pdf |archive-date=2010-12-28 }}.</ref>新增的情绪是:  

然而，在20世纪90年代，埃克曼扩展了他的基本情绪列表，包括一系列积极和消极的情绪，这些情绪并非都对应于面部肌肉。<ref>{{Cite book|last=Ekman |first=Paul |year=1999 |url=http://www.paulekman.com/wp-content/uploads/2009/02/Basic-Emotions.pdf |contribution=Basic Emotions |editor1-first=T |editor1-last=Dalgleish |editor2-first=M |editor2-last=Power |title=Handbook of Cognition and Emotion |place=Sussex, UK |publisher=John Wiley & Sons |url-status=dead |archive-url=https://web.archive.org/web/20101228085345/http://www.paulekman.com/wp-content/uploads/2009/02/Basic-Emotions.pdf |archive-date=2010-12-28 }}.</ref>新增的情绪是:  

<nowiki>#</nowiki> 娱乐  

<nowiki>#</nowiki> 娱乐  

==== 面部行为编码系统 ====

==== 面部行为编码系统 ====

心理学家已经构想出一个系统，用来正式分类脸上情绪的物理表达。面部动作编码系统 (FACS) 的中心概念是由保罗·埃克曼（ Paul Ekman ）和 华莱士·V·弗里森（Wallace V. Friesen） 在 1978 年基于 Carl-Herman Hjortsjö <ref name=":16">[http://face-and-emotion.com/dataface/facs/description.jsp "Facial Action Coding System (FACS) and the FACS Manual"] {{webarchive |url=https://web.archive.org/web/20131019130324/http://face-and-emotion.com/dataface/facs/description.jsp |date=October 19, 2013 }}. A Human Face. Retrieved 21 March 2011.</ref>的早期工作创建的，动作单位 (Action unit, AU)是核心概念。它们基本上是一块或多块肌肉的收缩或放松。心理学家根据他们的行为单位，提出了以下六种基本情绪的分类(这里的“ +”是指“和”) :

心理学家已经构想出一个系统，用来正式分类脸上情绪的物理表达。面部动作编码系统 (FACS) 的中心概念是由保罗·埃克曼（ Paul Ekman ）和 华莱士·V·弗里森（Wallace V. Friesen） 在 1978 年基于 Carl-Herman Hjortsjö <ref name=":16">[http://face-and-emotion.com/dataface/facs/description.jsp "Facial Action Coding System (FACS) and the FACS Manual"]. A Human Face. Retrieved 21 March 2011.</ref>的早期工作创建的，动作单位 (Action unit, AU)是核心概念。它们基本上是一块或多块肌肉的收缩或放松。心理学家根据他们的行为单位，提出了以下六种基本情绪的分类(这里的“ +”是指“和”) :

{| class="wikitable sortable"

{| class="wikitable sortable"

=== 医疗 ===

=== 医疗 ===

社会机器人，以及越来越多的机器人在医疗保健中的应用都受益于情感意识，因为它们可以更好地判断用户和病人的情感状态，并适当地改变他们的行为。在人口老龄化日益严重和缺乏年轻工人的国家，这一点尤为重要<ref name=":19">{{Cite book|title=Heart of the Machine: Our Future in a World of Artificial Emotional Intelligence|last=Yonck|first=Richard|publisher=Arcade Publishing|year=2017|isbn=9781628727333|location=New York|pages=150–153|oclc=956349457}}</ref>。

社会机器人，以及越来越多的机器人在医疗保健中的应用都受益于情感意识，因为它们可以更好地判断用户和病人的情感状态，并适当地改变他们的行为。在人口老龄化日益严重和缺乏年轻工人的国家，这一点尤为重要<ref name=":19">{{Cite book|title=Heart of the Machine: Our Future in a World of Artificial Emotional Intelligence|last=Yonck|first=Richard|publisher=Arcade Publishing|year=2017|location=New York|pages=150–153|oclc=956349457}}</ref>。

情感计算也被应用于交流技术的发展，以供孤独症患者使用<ref name=":20">[http://affect.media.mit.edu/projects.php Projects in Affective Computing]</ref>。情感计算项目文本中的情感成分也越来越受到关注，特别是它在所谓的情感或'''情感互联网'''中的作用<ref name=":21">Shanahan, James; Qu, Yan; Wiebe, Janyce (2006). ''Computing Attitude and Affect in Text: Theory and Applications''. Dordrecht: Springer Science & Business Media. p. 94. {{ISBN|1402040261}}</ref>。

情感计算也被应用于交流技术的发展，以供孤独症患者使用<ref name=":20">[http://affect.media.mit.edu/projects.php Projects in Affective Computing]</ref>。情感计算项目文本中的情感成分也越来越受到关注，特别是它在所谓的情感或'''情感互联网'''中的作用<ref name=":21">Shanahan, James; Qu, Yan; Wiebe, Janyce (2006). ''Computing Attitude and Affect in Text: Theory and Applications''. Dordrecht: Springer Science & Business Media. p. 94.</ref>。

=== 电子游戏 ===

=== 电子游戏 ===

情感型电子游戏可以通过'''生物反馈设备'''获取玩家的情绪状态<ref name=":22">{{cite conference |title=Affective Videogames and Modes of Affective Gaming: Assist Me, Challenge Me, Emote Me |first1=Kiel Mark |last1=Gilleade |first2=Alan |last2=Dix |first3=Jen |last3=Allanson |year=2005 |conference=Proc. [[Digital Games Research Association|DiGRA]] Conf. |url=http://comp.eprints.lancs.ac.uk/1057/1/Gilleade_Affective_Gaming_DIGRA_2005.pdf |access-date=2016-12-10 |archive-url=https://web.archive.org/web/20150406200454/http://comp.eprints.lancs.ac.uk/1057/1/Gilleade_Affective_Gaming_DIGRA_2005.pdf |archive-date=2015-04-06 |url-status=dead }}</ref>。有一些特别简单的生物反馈形式，如通过游戏手柄来测量按下按钮的压力，来获取玩家的唤醒度水平<ref name=":23">{{Cite conference| doi = 10.1145/765891.765957| title = Affective gaming: Measuring emotion through the gamepad| conference = CHI '03 Extended Abstracts on Human Factors in Computing Systems| year = 2003| last1 = Sykes | first1 = Jonathan| last2 = Brown | first2 = Simon| isbn = 1581136374| citeseerx = 10.1.1.92.2123}}</ref>； 另一方面是'''脑机接口'''<ref name=":24">{{Cite journal | doi = 10.1016/j.entcom.2009.09.007| title = Turning shortcomings into challenges: Brain–computer interfaces for games| journal = Entertainment Computing| volume = 1| issue = 2| pages = 85–94| year = 2009| last1 = Nijholt | first1 = Anton| last2 = Plass-Oude Bos | first2 = Danny| last3 = Reuderink | first3 = Boris| bibcode = 2009itie.conf..153N| url = http://wwwhome.cs.utwente.nl/~anijholt/artikelen/intetain_bci_2009.pdf}}</ref><ref name=":25">{{Cite conference| doi = 10.1007/978-3-642-02315-6_23| title = Affective Pacman: A Frustrating Game for Brain–Computer Interface Experiments| conference = Intelligent Technologies for Interactive Entertainment (INTETAIN)| pages = 221–227| year = 2009| last1 = Reuderink | first1 = Boris| last2 = Nijholt | first2 = Anton| last3 = Poel | first3 = Mannes| isbn = 978-3-642-02314-9}}</ref> 。情感游戏已被用于医学研究，以改善自闭症儿童的情感发展<ref name=":26">{{Cite journal

情感型电子游戏可以通过'''生物反馈设备'''获取玩家的情绪状态<ref name=":22">{{cite conference |title=Affective Videogames and Modes of Affective Gaming: Assist Me, Challenge Me, Emote Me |first1=Kiel Mark |last1=Gilleade |first2=Alan |last2=Dix |first3=Jen |last3=Allanson |year=2005 |conference=Proc.DiGRA Conf. |url=http://comp.eprints.lancs.ac.uk/1057/1/Gilleade_Affective_Gaming_DIGRA_2005.pdf |access-date=2016-12-10 |archive-url=https://web.archive.org/web/20150406200454/http://comp.eprints.lancs.ac.uk/1057/1/Gilleade_Affective_Gaming_DIGRA_2005.pdf |archive-date=2015-04-06 |url-status=dead }}</ref>。有一些特别简单的生物反馈形式，如通过游戏手柄来测量按下按钮的压力，来获取玩家的唤醒度水平<ref name=":23">{{Cite conference| doi = 10.1145/765891.765957| title = Affective gaming: Measuring emotion through the gamepad| conference = CHI '03 Extended Abstracts on Human Factors in Computing Systems| year = 2003| last1 = Sykes | first1 = Jonathan| last2 = Brown | first2 = Simon| citeseerx = 10.1.1.92.2123}}</ref>； 另一方面是'''脑机接口'''<ref name=":24">{{Cite journal | doi = 10.1016/j.entcom.2009.09.007| title = Turning shortcomings into challenges: Brain–computer interfaces for games| journal = Entertainment Computing| volume = 1| issue = 2| pages = 85–94| year = 2009| last1 = Nijholt | first1 = Anton| last2 = Plass-Oude Bos | first2 = Danny| last3 = Reuderink | first3 = Boris| bibcode = 2009itie.conf..153N| url = http://wwwhome.cs.utwente.nl/~anijholt/artikelen/intetain_bci_2009.pdf}}</ref><ref name=":25">{{Cite conference| doi = 10.1007/978-3-642-02315-6_23| title = Affective Pacman: A Frustrating Game for Brain–Computer Interface Experiments| conference = Intelligent Technologies for Interactive Entertainment (INTETAIN)| pages = 221–227| year = 2009| last1 = Reuderink | first1 = Boris| last2 = Nijholt | first2 = Anton| last3 = Poel | first3 = Mannes}}</ref> 。情感游戏已被用于医学研究，以改善自闭症儿童的情感发展<ref name=":26">{{Cite journal

  | pmid = 19592726

  | pmid = 19592726

| year = 2009

| year = 2009