Recognition of emotion using non-linear dynamics of speech

Author

Harimi, Ali ; Shahzadi, Ali ; Ahmadyfard, Alireza

Author_Institution

Dept. of Electr. & Comput. Eng., Semnan Univ., Semnan, Iran

fYear

2014

fDate

9-11 Sept. 2014

Firstpage

446

Lastpage

451

Abstract

Recognition of human´s emotion from speech has become one of the most challenging and attractive fields of research in speech processing area. The present study aimed to detect valence of emotions, using Non-Linear Dynamic features (NLDs). NLDs are extracted from the Discrete Cosine Transform (DCT) of descriptor contours computed from Phase Space Reconstruction (PSR) of speech. These features are used to estimate emotion primitives in 3D continuous emotion space on the VAM database using Support Vector Regression (SVR) under the Leave-One-Out (LOO) testing technique. Feature selection is performed using Sequential Forward Selection (SFS). Activation, valence and dominance of emotions are estimated by the best correlation of 85.06%, 53.39% and 84.68%, respectively.

Keywords

correlation methods; discrete cosine transforms; emotion recognition; feature extraction; feature selection; regression analysis; speech recognition; support vector machines; 3D continuous emotion space; LOO testing technique; Leave-One-Out testing technique; NLD feature extraction; PSR; SFS; SVR; VAM database; correlation method; descriptor contour DCT; discrete cosine transform; emotion activation; emotion dominance; emotion valence detection; feature selection; human emotion recognition; phase space reconstruction; sequential forward selection; speech nonlinear dynamic feature extraction; speech processing; support vector regression; Correlation; Correlation coefficient; Databases; Emotion recognition; Feature extraction; Speech; Speech recognition; Non-Linear Dynamic features; Phase Space Reconstruction; Speech emotion recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Telecommunications (IST), 2014 7th International Symposium on

Conference_Location

Tehran

Print_ISBN

978-1-4799-5358-5

Type

conf

DOI

10.1109/ISTEL.2014.7000745

Filename

7000745