文献类型：期刊文献

中文题名：一种基于Bark域能量分布的噪声分类方法

英文题名：A Noise Classification Method Based on Noise Energy Distribution in Bark Domain

作者：袁文浩[1];林家骏[1];陈宁[1];王雨[1]

机构：[1]华东理工大学信息科学与工程学院,上海200237

年份：2013

卷号：39

期号：4

起止页码：472

中文期刊名：华东理工大学学报（自然科学版）

外文期刊名：Journal of East China University of Science and Technology

收录：CSTPCD;;Scopus;北大核心:【北大核心2011】；CSCD:【CSCD2013_2014】；

基金：国家自然科学基金(60903186;61271349)

语种：中文

中文关键词：噪声分类;支持向量机;Bark域;能量分布特性

外文关键词：noise classification; SVM; Bark domain; energy distribution characteristics

摘要：对不同种类噪声的分类处理,可以提高噪声环境下语音信号处理的性能。为了能够准确地区分各类噪声,提出了一种基于Bark域噪声能量分布特性的噪声分类方法。通过将噪声能量从均匀时频空间映射到Bark空间,构造了一个能够有效区分各种噪声的22维特征向量,并使用支持向量机(SVM)进行模型训练和噪声分类。实验结果表明:所提出的噪声分类方法具有非常高的分类准确率,对用于实验的两种噪声数据集的平均分类准确率分别为99.50%和93.44%。
By classifying various noises, the performance of the speech signal processing in the noise environments can he improved. In order to accurately distinguish various noises, this paper proposes a noise classification method based on the distribution characteristics of the noise energy in the Bark domain. By mapping the noise energy from the uniform time-frequency space to the Bark space, this algorithm constructs a 22-dimensional feature vector that can effectively distinguish various noises. Moreover, the support vector machine （SVM） is utilized to train the model and classify the noises. Experimental results show that the proposed method has very high classification accuracy, and the average accuracies for two noise databases used in the experiments attain 99. 50% and 93.44%.