Title: Research on high accuracy mandarin emotion recognition method based on local optimal algorithms

Authors: Caihua Chen

Addresses: Hunan Radio and TV University, Changsha 410007, China

Abstract: In order to overcome the problem that the traditional Mandarin emotion recognition method does not optimise the result of emotion classification, which leads to low accuracy and recognition efficiency, a high-precision Mandarin emotion recognition method based on local optimisation algorithm is proposed. The emotion database of Putonghua is constructed by the dimension emotion model. On this basis, the emotion signals of Putonghua speech are pre-processed and extracted. Through clustering analysis, emotion features are statistically calculated and classified, and local optimisation algorithm is used to optimise the classification results to achieve high-precision recognition of Mandarin emotion. The experimental results show that compared with the traditional method, the accuracy and recognition efficiency of the proposed method have been improved to a certain extent, and the shortest recognition time is only 19 ms.

Keywords: local optimisation algorithm; high precision; Mandarin emotion recognition; emotion feature extraction.

DOI: 10.1504/IJICT.2021.115591

International Journal of Information and Communication Technology, 2021 Vol.18 No.4, pp.434 - 448

Received: 23 Nov 2019
Accepted: 09 Jan 2020

Published online: 11 Jun 2021 *

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