The Research of Speech Emotion Recognition Based on Gaussian Mixture Model

Abstract:

A new recognition method based on Gaussian mixture model for speech emotion recognition is proposed in this paper. To improve the effectiveness of feature extraction and accuracy of emotion recognition, extraction of Mel frequency cepstrum coefficient combined with Gaussian mixture model is used to recognize speech emotion. According to feature parameters extraction method by analyzing the principle of vocalization theory, emotion models based on Gaussian mixture model are generated and the similarity of their templates is obtained. A series of experiments is performed with recorded speech based on Gaussian mixture model and indicates the system gains high performance and better robustness.

• Periodical: Applied Mechanics and Materials (Volumes 668-669)
• Pages: 1126-1129
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.668-669.1126
• Online since: October 2014
• Authors: Wan Li Zhang, Guo Xin Li, Wei Gao
• Keywords: Feature Extraction, Gaussian Mixture Model, Mel Frequency Cepstrum Coefficient, Speech Emotion Recognition

References

[1] Lin Zhong , Yanxiong Li , Xin Wei, Guanglong Li , Zili Wang , Yewen Jiang. System design for monitoring infant speech emotion, 2013 10th IEEE International Conference on Control and Automation, (2013).

DOI: 10.1109/icca.2013.6564891

[2] Yuanlu Kuang, Lijuan Li. Speech emotion recognition of decision fusion based on DS evidence theory, Software Engineering and Service Science (ICSESS), (2013).

DOI: 10.1109/icsess.2013.6615425

[3] Wenming Zheng , Minghai Xin , Xiaolan Wang, Bei Wang. A Novel Speech Emotion Recognition Method via Incomplete Sparse Least Square Regression , Signal Processing Letters, (2014).

DOI: 10.1109/lsp.2014.2308954

[4] Qingli Zhang , Ning An , Kunxia Wang , Fuji Ren , Lian Li. Speech emotion recognition using combination of features, 2013 Fourth International Conference on Intelligent Control and Information Processing, (2013).

DOI: 10.1109/icicip.2013.6568131

[5] Krishna Kishore, K.V. ; Krishna Satish, P. Emotion recognition in speech using MFCC and wavelet features, 2013 IEEE 3rd International Advance Computing Conference , (2013).

DOI: 10.1109/iadcc.2013.6514336

[6] Sungrack Yun , Yoo, C.D. Loss-Scaled Large-Margin Gaussian Mixture Models for Speech Emotion Classification. Audio, Speech, and Language Processing, (2012).

DOI: 10.1109/tasl.2011.2162405

[7] Jianbo Jiang ; Zhiyong Wu ; Mingxing Xu ; Jia Jia ; Lianhong Cai. Comparing feature dimension reduction algorithms for GMM-SVM based speech emotion recognition, Signal and Information Processing Association Annual Summit and Conference, (2013).

DOI: 10.1109/apsipa.2013.6694336

[8] Bhaykar, Manav ; Yadav, Jainath ; Rao, K. Sreenivasa . Speaker dependent, speaker independent and cross language emotion recognition from speech using GMM and HMM, 2013 National Conference on Communications (NCC), (2013).

DOI: 10.1109/ncc.2013.6487998

[9] Tsang-Long Pao, Chun-Hsiang Wang , Yu-Ji Li. A Study on the Search of the Most Discriminative Speech Features in the Speaker Dependent Speech Emotion Recognition, 2012 Fifth International Symposium on  Parallel Architectures, Algorithms and Programming, (2012).

DOI: 10.1109/paap.2012.31

[10] Wanli zhang, Guoxin Li. The Research of Feature Extraction Based on MFCC for Speaker Recognition . 3rd International Conference on Computer Science and Network Technology, October (2013).

DOI: 10.1109/iccsnt.2013.6967289