Sound events separation and recognition using LiSparse complex nonnegative matrix factorization and multi-class mean supervector support vector machine

P. Parathai, N. Tengtrairat, W. L. Woo
{"title":"Sound events separation and recognition using LiSparse complex nonnegative matrix factorization and multi-class mean supervector support vector machine","authors":"P. Parathai, N. Tengtrairat, W. L. Woo","doi":"10.1109/INCIT.2017.8257878","DOIUrl":null,"url":null,"abstract":"This paper proposes a novel single channel sound separation and events recognition method. First, the sound separation step is based on a complex nonnegative matrix factorization (CMF) with probabilistically optimal L1 sparsity which decomposes an information-bearing matrix into twodimensional convolution of factor matrices that represent the spectral basis and temporal code of the sources. The L1 sparsity CMF method can extract recurrent patterns of magnitude spectra that underlie observed complex spectra and the phase estimates of constituent signals, thus enabling the features of the components to be extracted more efficiently. Second, the event recognition step is built by using the multi-class mean supervector support vector (MS-SVM) machine. The separated signal from the first step is segmented by using the sliding window function and then extract features of each block. The major features which are zero-crossing rate, Mel frequency cepstral coefficients, and short-time energy are investigated to classify sound events signal into defined classes. The mean supervector is encoded from the obtained features. The multi-class MS-SVM method has been examined the recognition performance by modeling with various features. The experimental results show the robustness and efficiency of the proposed method.","PeriodicalId":405827,"journal":{"name":"2017 2nd International Conference on Information Technology (INCIT)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 2nd International Conference on Information Technology (INCIT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/INCIT.2017.8257878","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

This paper proposes a novel single channel sound separation and events recognition method. First, the sound separation step is based on a complex nonnegative matrix factorization (CMF) with probabilistically optimal L1 sparsity which decomposes an information-bearing matrix into twodimensional convolution of factor matrices that represent the spectral basis and temporal code of the sources. The L1 sparsity CMF method can extract recurrent patterns of magnitude spectra that underlie observed complex spectra and the phase estimates of constituent signals, thus enabling the features of the components to be extracted more efficiently. Second, the event recognition step is built by using the multi-class mean supervector support vector (MS-SVM) machine. The separated signal from the first step is segmented by using the sliding window function and then extract features of each block. The major features which are zero-crossing rate, Mel frequency cepstral coefficients, and short-time energy are investigated to classify sound events signal into defined classes. The mean supervector is encoded from the obtained features. The multi-class MS-SVM method has been examined the recognition performance by modeling with various features. The experimental results show the robustness and efficiency of the proposed method.
基于LiSparse复非负矩阵分解和多类均值超向量支持向量机的声音事件分离与识别
提出了一种新的单通道声音分离和事件识别方法。首先,声音分离步骤基于具有概率最优L1稀疏性的复杂非负矩阵分解(CMF),该分解将承载信息的矩阵分解为表示声源的频谱基和时间码的因子矩阵的二维卷积。L1稀疏度CMF方法可以提取观测到的复光谱和组成信号的相位估计基础上的星等谱的循环模式,从而能够更有效地提取成分的特征。其次,利用多类均值超向量支持向量机(MS-SVM)构建事件识别步骤;将第一步分离出来的信号利用滑动窗口函数进行分割,然后提取每个块的特征。研究了声事件信号的过零率、低频倒谱系数和短时能量等主要特征,将声事件信号进行了分类。根据得到的特征对均值超向量进行编码。通过对多类MS-SVM方法进行特征建模,检验了该方法的识别性能。实验结果表明了该方法的鲁棒性和有效性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信