Study of Speech Emotion Recognition Based on Improved Elman Neural Network
WANG Ying
Abstract：Speech emotion features can be divided into the global statistical feature and instantaneous characteristics on the time granularity. According to the dynamic characteristics of speech emotion,this paper presents a realization of speech emotion rec-ognition improved Elman neural network model. The improved Elman network receive global feature signal and the time sequence signal as input,and modify the network structure automatically according to the input signal characteristics. This new Elman net-work fuses the global feature of signal and the time sequence signal successfully,and enhances the discrimination of the whole system.
Keywords：speech emotion featuresimproved Elman neural networkglobal feature signaltime sequence signal
Publication Date：2017-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 2131-2135 )