Title: Optimal prototype selection for speech emotion recognition using fuzzy k-important nearest neighbour

Authors: Zhen Xing Zhang; Joon Shik Lim; Zhao Cai Jiang; Chun Jie Zhou; Shao Jing Li

Addresses: School of Information and Electrical Engineering, Ludong University, 186, Middle Hongqi Road, Zhifu District, Yantai City, Shandong Province, China ' IT College, Gachon University, 65 Bokjeong-dong, Sujeong-gu, Seongnam City, Gyeonggi-do, South Korea ' School of Educational Science, Ludong University, 186, Middle Hongqi Road, Zhifu District, Yantai City, Shandong Province, China ' School of Information and Electrical Engineering, Ludong University, 186, Middle Hongqi Road, Zhifu District, Yantai City, Shandong Province, China ' Science and Information College, Qingdao Agricultural University, 700, Changcheng Road, Chengyang District, Qingdao City, Shandong Province, China

Abstract: Speech emotion recognition has been a popular topic of affective computing. Accuracy in speech emotion recognition depends on selecting the optimal prototype. In this paper, a new 2-D emotional speech recognition model based on a fuzzy k-important nearest neighbour (FKINN) and neuro-fuzzy network is described. In the FKINN algorithm, an important nearest neighbour selection rule is introduced. The neuro-fuzzy network applies a bounded sum of weighted fuzzy membership functions (BSWFM). During the training process, BSWFM calculates the Takagi-Sugeno defuzzification values for the 2-D visual model. The emotional speech signals used in this work were obtained from the Berlin emotional speech database. The proposed new model achieves 83.5% overall classification accuracy with the 2-D emotional speech recognition model. The classification accuracies of anger, happiness, sadness, and neutral were 94.1%, 65.9%, 81.1%, and 87.5%, respectively.

Keywords: speech recognition; emotion recognition; prototype selection; k-nearest neighbour; kNN; optimisation; affective computing; emotions; neuro-fuzzy networks; neural networks; fuzzy logic; emotional speech signals; anger; happiness; sadness; neutral.

DOI: 10.1504/IJCNDS.2016.079096

International Journal of Communication Networks and Distributed Systems, 2016 Vol.17 No.2, pp.103 - 119

Received: 11 Mar 2016
Accepted: 30 Mar 2016

Published online: 12 Sep 2016 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article