计算机科学 ›› 2015, Vol. 42 ›› Issue (11): 270-273.doi: 10.11896/j.issn.1002-137X.2015.11.055

• 人工智能 • 上一篇    下一篇

基于PCA和SVM的普通话语音情感识别

蒋海华,胡 斌   

  1. 北京工业大学计算机学院 北京100124,北京工业大学电子信息与控制工程学院 北京100124
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受国家重点基础研究发展计划项目(2014CB744600),北京市科学技术研究院创新团队项目(IG201203N)资助

Speech Emotion Recognition in Mandarin Based on PCA and SVM

JIANG Hai-hua and HU Bin   

  • Online:2018-11-14 Published:2018-11-14

摘要: 在语音情感识别中,情感特征的选取与抽取是重要环节。目前,还没有非常有效的语音情感特征被提出。因此,在包含6种情感的普通话情感语料库中,根据普通话不同于西方语种的特点,选取了一些有效的情感特征,包含Mel频率倒谱系数、基频、短时能量、短时平均过零率和第一共振峰等,进行提取并计算得到不同的统计量;接着采用主成分分析(PCA)进行抽取;最后利用基于支持向量机(SVM)的语音情感识别系统进行分类。实验结果表明, 与其他一些重要的研究结果相比,该方法得到了较高的平均情感识别率, 且情感特征的选取、抽取及建模是合理、有效的。

关键词: 语音情感识别,主成分分析,支持向量机

Abstract: Feature selection and extraction play a vital role in speech emotion recognition.At present,no effective speech emotion features are proposed.For these reasons,according to the characteristic of Mandarin which is different from western languages,some effective emotional features and related statistics,including Mel-frequency cepstral coefficients,pitch frequency,short-time energy,short-time average zerocrossing rate,the first formant and so on,were analyzed on a Mandarin emotional corpus which contains 6 kinds of emotions.Then we chose principal component analysis (PCA) for extraction and presented a speech emotion recognition method based on support vector machine (SVM) for classification.The experimental results show that the proposed method achieves high emotion recognition accuracy compared with several significant methods,and the emotion extraction and modeling are reasonable and effective.

Key words: Speech emotion recognition,PCA,SVM

[1] 韩文静,李海峰,阮华斌,等.语音情感识别研究进展综述[J].软件学报,2014,5(1):37-50Han Wen-jing,Li Hai-feng,Ruan Hua-bin,et al.Review onspeech emotion recognition[J].Journal of Software,2014,25(1):37-50
[2] Origlia A,Galata V,Ludusan B.Automatic classification of emotions via global and local prosodic features on a multilingual emotional database[C]∥ Proc.of the 2010 Speech Prosody.Chicago,2010
[3] Seppnen T,Vayrynen E,Toivanen J.Prosody-Based classifycation of emotions in spoken finnish[C]∥Proc.of the 2003 European Conf.on Speech Communication and Technology (EUROSPEECH).Geneva:ISCA,2003:717-720
[4] Li Xi,Tao Ji-dong,Johnson M T,et al.Stress and emotion classification using jitter and shimmer features[C]∥Proc.of the 2007 IEEE International Conference on Acoustics,Speech,and Signal Processing (ICASSP).Honolulu:IEEE Computer,2007:1081-1084
[5] Nwe T L,Foo S W,Silva L C D.Speech emotion recognitionusing hidden Markov models[J].Speech Communication,2003,1(4):603-623
[6] Breazeal C,Aryananda L.Recognition of affective communicative intent in robot-directed speech[J].Autonomous Robots,2002,2(1):83-104
[7] Nicholson J,Takahashi K,Nakatsu R.Emotion recognition in speech using neural networks[J].Neural Computing & Applications,2000,9(4):290-296
[8] Institute of Automation,Chinese Academy of Sciences.CASIA Mandarin emotional corpus [DB/OL].http://www.chinese-ldc.org/resource_info.php?rid=76Casis
[9] Benesty J,Sondhi M M,Huang Y.Springer Handbook onSpeech Processing[M].Berlin:Springer-Verlag,2008
[10] Gobl C,Chasaide A N.The role of voice quality in communicating emotion,mood and attitude[J].Speech Communication,2003,0(1/2):189-212
[11] 赵力.语音信号处理(第2版)[M].北京:机械工业出版社,2011:51-52 Zhao Li.Speech signal processing(Second Edition)[M].Beijing:China Machine Press,2011:51-52
[12] Lee C M,Narayanan S S,Pieraccini R.Classifying emotion-ns in human-machine spoken dialogs[C]∥Proceedings of IEEE International Conference on Multimedia and Expo.Lusanne,Switzerland,2002:737-740
[13] Chuang Ze-jing,Wu Chung-hsien.Emotion recognition using acoustic features and textual content[C]∥Proceedings of IEEE International Conference on Multimedia and Expo.Taipei,Taiwan,2004:53-56
[14] 罗宪华,杨大利,徐明星,等.面向非特定人语音情感识别的PCA特征选择方法[J].计算机科学,2011,8(8):212-213 Luo Xian-hua,Yang Da-li,Xu Ming-xing,et al.PCA Based Feature Selection Algorithm on Speaker-independent Speech Emotion Recognition[J].Computer Science,2011,8(8):212-213
[15] 尤鸣宇.语音情感识别的关键技术研究[D].杭州:浙江大学,2007 You Ming-yu.Research on Key Techniques of Speech Emotion Recognition[D].Hangzhou:Zhejiang University,2007

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!