EMD-TEO Based Speech Emotion Recognition

Speech emotion recognition is an important issue in the development of human-robot interactions (HRI). This paper describes the realization of emotional interaction for an intelligent emotional robot, focusing on speech emotion recognition. The empirical mode decomposition based signal reconstruction method is utilized to conduct the feature extraction. With this approach, a novel feature called SMFCC was proposed. Afterwards, two improvements were carried out and novel features were obtained to further increase the recognition rate. One is using the linear weighting rule defined is this paper, while the other is combination with the teager energy operator. In the experiments, seven status of emotion were selected to be recognized and the highest 81.43% recognition rate was achieved. The numerical results indicate that the proposed features are robust and the performance of speech emotion recognition is improved substantially.

[1]  W. Timothy Liu,et al.  Interpretation of scatterometer ocean surface wind vector EOFs over the Northwestern Pacific , 2003 .

[2]  Chongchong Yu,et al.  A Study and Application of HHT in Vibration Signal Analysis of Bridge Structural Health Monitoring System , 2009, 2009 2nd International Congress on Image and Signal Processing.

[3]  Rohit Moghe,et al.  Trend analysis techniques for incipient fault prediction , 2009, 2009 IEEE Power & Energy Society General Meeting.

[4]  John H. L. Hansen,et al.  Nonlinear feature based classification of speech under stress , 2001, IEEE Trans. Speech Audio Process..

[5]  N. Huang,et al.  The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis , 1998, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[6]  J. Marsden,et al.  A mathematical introduction to fluid mechanics , 1979 .

[7]  J. F. Kaiser,et al.  On a simple algorithm to calculate the 'energy' of a signal , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[8]  Yong Jung Kim.  A MATHEMATICAL INTRODUCTION TO FLUID MECHANICS , 2008 .

[9]  Astrid Paeschke,et al.  A database of German emotional speech , 2005, INTERSPEECH.

[10]  Jiang Yang-bo.  Application of Hilbert marginal spectrum in speech emotion recognition , 2009 .

[11]  Shen Huai-rong.  Research and Comparison on the Application of Hilbert-Huang Transform and Wavelet Transform to Fault Feature Extraction , 2009 .

[12]  Nii O. Attoh-Okine,et al.  Comparative study of Hilbert–Huang transform, Fourier transform and wavelet transform in pavement profile analysis , 2009 .

[13]  Gao Hui,et al.  Emotion classification of mandarin speech based on TEO nonlinear features , 2007, SNPD.

[14]  Li Yingmin,et al.  Analysis of earthquake ground motions using an improved Hilbert–Huang transform , 2008 .

[15]  Yong Huang,et al.  Detection and location of power quality disturbances based on mathematical morphology and hilbert-huang transform , 2009, 2009 9th International Conference on Electronic Measurement & Instruments.

[16]  T. Y. Wu,et al.  Misalignment diagnosis of rotating machinery through vibration analysis via the hybrid EEMD and EMD approach , 2009 .

[17]  Huang Biao,et al.  Analysis of the characteristics of gastrointestinal motility based on Hilbert-Huang transform method , 2008 .

[18]  T. J. Thomas.  A finite element model of fluid flow in the vocal tract , 1986 .