Speech Emotion Recognition Based on EMD in Noisy Environments

Abstract:

In the speech emotion recognition process, How to obtain effective characteristic parameters from the emotional data including the noise is one of the significant and difficult problem. This paper first removes the gauss white noise with the adaptive filter. Then the Mel Frequency Cepstrum Coefficients (MFCC) based on Empirical Mode Decomposition (EMD) is extracted and with its difference parameter to improve. At last we present an effective method for speech emotion recognition based on Fuzzy Least Squares Support Vector Machines (FLSSVM) so as to realize the speech recognition of four main emotions, i.e, anger, happy, surprise and natural. The experiment results show that this method has the better anti-noise effect when compared with traditional Support Vector Machines (SVM).

• Periodical: Advanced Materials Research (Volume 831)
• Pages: 460-464
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.831.460
• Online since: December 2013
• Authors: Yun Yun Chu, Wei Hua Xiong*, Wei Chen
• Keywords: Adaptive Filter, Empirical Mode Decomposition (EMD), Fuzzy Least Squares Support Vector Machines, MFCC

References

[1] JUAN M M, ARANTZA A.: Emotions in human and artificial inteligence[J]. Computers in Human Behavior vol. 2(2005), pp.323-341.

[2] L. Zhao: Speech Signal Processing[M], China Machine Press, Beijing (2003), in Chinese.

[3] Cynthia Breazeal: Emotion and sociable humanoid robots. Journal of Human-Computer Studies vol. 59(2003), pp.119-155.

DOI: 10.1016/s1071-5819(03)00018-1

[4] D. Ververidis and C. Kotropoulos: Emotional speech recognition: Resources, features, and methods. Speech Comunnication vol. 48(2006), p.1162–1181.

DOI: 10.1016/j.specom.2006.04.003

[5] Fuhai Li, Jinwen Ma, and Dezhi huang: MFCC and SVM Based Recognition of Chinese Vowels. Computational Intelligence and Security-International Conference, vol(2005), pp.812-819.

DOI: 10.1007/11596981_118

[6] Shao, Y., Liu, B., Li, Z.: Speaker Recognition System Based on MFCC and Weighted Vector Quantization. Computer Engineering and Applications, vol. 5(2002), p.127–128, in Chinese.

[7] Gan Lu, Long Zhou and Xinge You: An improved EMD analysis method for GPR images. International Conference on Computational and Information Sciences(2011), pp.104-107.

DOI: 10.1109/iccis.2011.77

[8] Yilin Lin, Gang Wei: Speech Emotion Recognition Based on HMM and SVM. Proceedings of the Fourth International Conference on Machine Learning and Cybernetics(2005), pp.18-21.

DOI: 10.1109/icmlc.2005.1527805

[9] Weijun Wang, Dongguang Zuo: Speech de-noising method based on adaptive filtering[J]. Modern Electronics Technique Vol. 35(2012), pp.84-90.

[10] Binbin Tu and Fengqin YU: Speech Emotion Recognition Based on Improved MFCC with EMD. Computer Engineering and Applications (2012), pp.119-122, in Chinese.

[11] Yujin Yuan, Peihua Zhao, and Qun Zhou: Research of Speaker Recognition Based on Combination of LPCC and MFCC. International Conference on Intelligent Computing and Intelligent Systems v3(2010), pp.765-767.

DOI: 10.1109/icicisys.2010.5658337

[12] Shiqing Zhang: Speech emotion recognition based on fuzzy least squares support vector machines[C]. Proceedings of Seventh World Congress on Intelligence Control and Automation. Chongqing(2008), pp.1299-1302.

DOI: 10.1109/wcica.2008.4594449