摘要
研究了基于卷积神经网络的语音情感识别算法,改进了传统卷积神经网络训练过程中的卷积核权值的更新算法,使卷积核权值的更新算法与迭代次数有关联;同时为了增加情感语音之间的特征差异性,将语音信号经过预处理后得到的梅尔频率倒谱系数特征数据矩阵进行变换,提高卷积神经网络的表达能力.实验表明,改进后的语音情感识别算法的错误识别率比传统算法的错误识别率约减少7%.
In this paper,we studied the algorithm of speech emotion recognition based on convolutional neural networks,and improved the algorithm of updating convolution kernel weight during the training process of traditional convolutional neural networks,resulting that the algorithm of updating the convolution kernel weight was related to the number of iterations.Simultaneously,in order to increase the difference of emotional phonetic features,the data matrix of the Mel-frequency cepstral coefficients(MFCC)obtained by preprocessing the speech signal was transformed,consequently,improved the expressive ability of convolutional neural networks.Experiments showed that the error recognition rate of the improved algorithm of speech emotion recognition was about 7%lower than that of traditional algorithms.
作者
曾润华
张树群
ZENG Run-hua;ZHANG Shu-qun(School of Information Science and Technology,Jinan University,Guangzhou 510632,China)
出处
《应用科学学报》
CAS
CSCD
北大核心
2018年第5期837-844,共8页
Journal of Applied Sciences
关键词
语音情感识别
卷积神经网络
梅尔频率倒谱系数
识别率
speech emotion recognition
convolutional neural networks
Mel-frequency cepstral coefficients(MFCC)
recognition rate
