基于单类支持向量机的音频分类  

Audio classification based on one-class SVM

作　　者：颜景斌[1] 吴石[1] 伊戈尔·艾杜阿尔达维奇 

机构地区：[1]哈尔滨理工大学电气与电子工程学院,哈尔滨150040 [2]白俄罗斯国立大学无线电物理与电子系,明斯克220050

出　　处：《计算机应用》2009年第5期1419-1422,共4页journal of Computer Applications

基　　金：白俄罗斯国立大学科学技术中心基金项目(2006-B-1375)

摘　　要：研究一种基于单类支持向量机的音频分类方法,能够使每一类样本都独立地获得一个决策函数,通过决策函数的最大值来判断样本所属的类。通过使用小波包变换提取语音特征向量,并融合多特征向量,将音频分为5类:纯语音、音乐、环境音、含背景音语音和静音。实验结果表明这种方法具有较好的分类精度,性能优于贝叶斯、隐马尔可夫模型和神经网络分类器。The author studied an audio classification method based on One-Class Support Vector Machine （OCSVM）, which could form a decision function for every single class sample and accordingly obtain the aim of classification based on maximum of decision function. By employing wavelet packed transformation to extract features of audio and integrating multiple features, five audio classes were made： pure speech, music, environmental sound, speech over background and silence. Experimental results show that OCSVM has better classification accuracy, and performs better than the other classification systems using the Bayes, Hidden Markov Model （HMM） and Neural Network （NN）.

关 键 词：单类支持向量机 音频分类 特征提取 小波 

分 类 号：TP391.42[自动化与计算机技术—计算机应用技术]