实用语音情感的特征分析与识别的研究

黄程韦; 赵艳; 金赟; 于寅骅; 赵力

doi:10.3724/SP.J.1146.2009.00886

实用语音情感的特征分析与识别的研究

doi: 10.3724/SP.J.1146.2009.00886

黄程韦^{*① 赵艳,},
赵艳,
金赟,
于寅骅,
赵力

基金项目:

国家自然科学基金(60472058，60975017，51075068)和江苏省自然科学基金(BK2008291)资助课题

计量
- 文章访问数: 3835
- HTML全文浏览量: 105
- PDF下载量: 1635
- 被引次数: 0
出版历程
- 收稿日期: 2009-06-16
- 修回日期: 2010-10-19
- 刊出日期: 2011-01-19

A Study on Feature Analysis and Recognition of Practical Speech Emotion

摘要

摘要: 该文针对语音情感识别在实际中的应用，研究了烦躁等实用语音情感的分析与识别。通过计算机游戏诱发的方式采集了高自然度的语音情感数据，提取了74种情感特征，分析了韵律特征、音质特征与情感维度之间的关系，对烦躁等实用语音情感的声学特征进行了评价与选择，提出了针对实际应用环境的可拒判的实用语音情感识别方法。实验结果表明，文中采用的语音情感特征，能较好识别烦躁等实用语音情感，平均识别率达到75%以上。可拒判的实用语音情感识别方法，对模糊的和未知的情感类别的分类进行了合理的决策，在语音情感的实际应用中具有重要的意义。
- 语音识别 /
- 实用语音情感 /
- 韵律特征 /
- 音质特征 /
- 拒判方法
Abstract: Practical speech emotions as impatience and happiness are studied especially for evaluation of emotional well-being in real world applications. Induced natural speech emotion data is collected with a computer game, 74 emotion features are extracted, prosody features and voice quality features are analyzed according to dimensional emotion model, evaluation and selection of acoustic features are carried out for practical emotions in this paper, a method of practical speech emotion classification with rejection decision is proposed for real world occasions. The experiment results show, the speech features analyzed in this paper are suitable for classification of practical speech emotions like impatience and happiness, average recognition rate is above 75%, and the method of emotion classification with rejection decision is necessary for the proper recognition decision of ambiguous or unknown emotion samples, especially for the real world challenges.
- Speech recognition /
- Practical speech emotion /
- Prosody features /
- Voice quality features /
- Rejection decision

HTML全文

参考文献(1)

Spellman B A and Willingham D T. Current Directions in Cognitive Science. Boston: Allyn Bacon, 2007: 1-3.[2]Picard R W. Affective Computing. Cambridge: MIT Press, 1997, Chapter 6.[3]Vinciarelli A, Pantic M, Bourlard H, and Pentland A. Social signal processing: survey of an emerging domain[J].Image Vision Computing.2009, 27(12):1743-1759[4]Cowie R, Douglas-Cowie E, Tsapatsoulis N, Votsis G, Kollias S, Fellenz W, and Taylor J G. Emotion recognition in human-computer interaction[J].IEEE Signal Processing Magazine.2001, 18(1):32-80[5]Scherer K R. Vocal communication of emotion: a review of research paradigms[J].Speech Communication.2003, 40(1/2):227-256[6]Zeng Z, Pantic M, Roisman G I, and Huang T. A survey of affect recognition methods: audio, visual and spontaneous expressions[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.2009, 31(1):39-58[7]Casale S, Russo A, Scebba G, and Serrano S. Speech emotion classification using machine learning algorithms. 2008 IEEE International Conference on Semantic Computing. Santa Clara, CA, USA, Aug. 4-7, 2008: 158-165.[8]Zhao Yan, Zhao Li, Zou Cai-rong, and Yu Yin-hua. Speech emotion recognition using modified quadratic discriminatioin function[J].Journal of Electronics (China.2008, 25(6):840-844[9]韩文静, 李海峰, 韩纪庆. 基于长短时特征融合的语音情感识别方法. 清华大学学报(自然科学版), 2008, 48(S1): 708-714.Han Wen-jing, Li Hai-feng, and Han Ji-qing. Speech emotion recognition with combined short and long term features. Journal of Tsinghua University (Science and Technology), 2008, 48(S1): 708-714.[10]Pao Tsang-long, Chen Yu-te, and Yeh Jun-heng. Emotion recognition and evaluation from mandarin speech signals. International Journal of Innovative Computing, Information and Control, 2008, 4(7): 1695-1709.[11]Johnstone T. Emotional speech elicited using computer games. Fourth International Conference on Spoken Language, Philadelphia, PA, USA, 1996, Vol. 3: 1985-1988.[12]Johnstone T, Van Reekum C M, hird K, and Kirsner K, et al.. Affective speech elicited with a computer game[J].Emotion.2005, 5(4):513-518[13]王治平,赵力,邹采荣. 基于基音参数规整及统计分布模型距离的语音情感识别. 声学学报, 2006, 31(1): 28-34.Wang Zhi-ping, Zhao Li, and Zou Cai-rong. Emotion speech recognition based on modified parameter and distance of statistical model of pitch. Acta Acustica, 2006, 31(1): 28-34.[14]Tato R S, Kompe R, and Pardo J M. Emotional space improves emotion recognition. ICSLP, Denver, Colorado, USA, 2002: 2029-2032.[15]Borchert M and Dusterhoft A. Emotions in speech - experiments with prosody and quality features in speech for use in categorical and dimensional emotion recognition environments. Proceeding of NLP-KE05, Wuhan, China, 2005: 147-151.Xiao Zhong-zhe, Dellandrea E, and Dou Wei-bei, et al.. Features extraction and selection for emotional speech classification. IEEE Conference on Advanced Video and Signal Based Surveillance, Como, Italy, 2005: 411-416.[16]Ho T and Basu M. Complexity measures of supervised classification problems. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 24(3): 289-300.[17]王治平. 情感语音信号特征分析与识别. [博士论文], 东南大学, 2004.[18]Wang Zhi-ping. Feature analysis and emotion recognition in emotional speech.[D.Ph. dissertation], Southeast University, 2004.

施引文献

资源附件(0)

访问统计