基于多特征融合的SVM声学场景分类算法研究  

Support Vector Machine for Acoustic Scene Classification Algorithm Research Based on Multi-Features Fusion

作　　者：赵薇[1] 靳聪[1] 涂中文[2] SRIDHAR Krishnan 刘杉[1] ZHAO Wei;JIN Cong;TU Zhong-wen;SRIDHAR Krishnan;LIU Shan(School of Information and Communication Engineering,Communication University of China,Beijing 100024,China;School of Broadcasting and Hosting Art,Communication University of China,Beijing 100024,China;Department of Electrical and Computer Engineering,Ryerson University,Toronto M5B 2K3,Canada)

机构地区：[1]中国传媒大学信息与通信工程学院,北京100024 [2]中国传媒大学播音主持艺术学院,北京100024 [3]加拿大怀雅逊大学电气和计算机工程系,多伦多M5B 2K3加拿大

出　　处：《北京理工大学学报》2020年第1期69-75,共7页Transactions of Beijing Institute of Technology

基　　金：国家自然科学基金资助项目(61631016,61901421);中央高校基本科研业务费专项基金(CUC19ZD003)

摘　　要：针对DCASE2017挑战赛的声场环境数据集,提取梅尔频率倒谱系数(MFCC)、短时能量(SE)、声学事件似然特征(AELF)、静音时间(MT)特征,组成多特征融合矩阵,通过对比多种核函数和寻优算法,最终选取高斯径向基核函数(RK)建立支持向量机(SVM)模型,采用交叉验证(CV)方法进行SVM参数寻优,对15种声学场景进行分类.实验结果表明,杂货店、办公室的分类准确性达到了90%以上,平均分类准确性达到71.11%,远高于挑战赛的基线系统61%的平均分类准确性.For the sound environment dataset of the DCASE 2017 Challenge,Mel frequency cepstral coefficients(MFCC),short-time energy(SE),acoustic event likelihood features(AELF),and mute time(MT)features were extracted to form a multi-features fusion matrix.Comparing various kernel functions and optimization algorithms,radial basis function kernel(RK)was finally selected to establish the support vector machine(SVM)model,and cross validation(CV)method was utilized to optimize SVM parameters and to classify 15 acoustic scenes.The experimental results show that the classification accuracy of grocery store and office can reach more than 90%,and the average classification accuracy reaches 71.11%,which is much higher than the average classification accuracy of 61%of the baseline system given in the challenge.

关 键 词：声学场景分类 支持向量机 参数寻优 特征融合 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]