高技术通讯2017，Vol.27Issue(11)：889-898,10.DOI:10.3772/j.issn.1002-0470.2017.11-12.002
基于卷积神经网络学习的语音情感特征降维方法研究
Research on a dimension reduction method of speech emotional feature based on convolution neural network
摘要
Abstract
A feature reduction method based on convolution neural network(CNN)is proposed to solve the problem of speech emotion recognition.On the basis of extracting a large number of features of the original speech emotion da-ta,the corresponding feature matrix is obtained by normalizing the different dimension features.The CNN is used to study the feature matrix,and the weights of the CNN network are analyzed.According to the characteristics of the network learning feature,that is,by comparing the activation weights of each class,the features that are most fa-vorable for classification are selected by calculation, so the feature selection criterion FR-CNN is obtained.The multi-modal emotional database CHEAVD provided by the Institute of Automation of Chinese Academy of Sciences is used to test all the eight kinds of emotional data,showing that the average recognition error rate of the CNN clas-sifier constructed with all the feature sets is reduced by 2.1%compared to the baseline results,while the average recognition error rate of the same CNN classifier constructed with dimension reduction F feature set is reduced by 9.4%.In addition,using only 15% of original feature set's features on the basis of dimensional reduction of a large number of features,can not only effectively increase the convergence speed of the classifier, but also make the recognition error rate reduced,at the same time in the actual speech emotion recognition system,the complexity of system can also be reduced.The study provides a new idea for the feature extraction of speech emotion.关键词
模式识别/语音情感/卷积神经网络(CNN)/特征优选准则/特征降维Key words
pattern recognition/speech emotion/convolutional neural network(CNN)/feature selection cri-terion/feature reduction引用本文复制引用
薄洪健,马琳,孔祥浩,李海峰..基于卷积神经网络学习的语音情感特征降维方法研究[J].高技术通讯,2017,27(11):889-898,10.基金项目
国家自然科学基金(61671187),深圳市基础研究(JCYJ20150929143955341,JCYJ20150625142543470)和语言语音教育部-微软重点实验室开放基金(HIT.KLOF.2015OXX,HIT.KLOF.2016OXX)资助项目. （61671187）
