A Salient Feature Extraction Algorithm for Speech Emotion Recognition

Ruiyu LIANG  Huawei TAO  Guichen TANG  Qingyun WANG  Li ZHAO  

IEICE TRANSACTIONS on Information and Systems   Vol.E98-D   No.9   pp.1715-1718
Publication Date: 2015/09/01
Publicized: 2015/05/29
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2015EDL8091
Type of Manuscript: LETTER
Category: Speech and Hearing
speech emotion recognition,  spectrogram,  selective attention,  support vector machine,  

Full Text: PDF(739.2KB)>>
Buy this Article

A salient feature extraction algorithm is proposed to improve the recognition rate of the speech emotion. Firstly, the spectrogram of the emotional speech is calculated. Secondly, imitating the selective attention mechanism, the color, direction and brightness map of the spectrogram is computed. Each map is normalized and down-sampled to form the low resolution feature matrix. Then, each feature matrix is converted to the row vector and the principal component analysis (PCA) is used to reduce features redundancy to make the subsequent classification algorithm more practical. Finally, the speech emotion is classified with the support vector machine. Compared with the tradition features, the improved recognition rate reaches 15%.