Recognition of acoustic events using deep neural networks

O. Gencoglu, T. Virtanen, H. Huttunen
{"title":"Recognition of acoustic events using deep neural networks","authors":"O. Gencoglu, T. Virtanen, H. Huttunen","doi":"10.5281/ZENODO.43987","DOIUrl":null,"url":null,"abstract":"This paper proposes the use of a deep neural network for the recognition of isolated acoustic events such as footsteps, baby crying, motorcycle, rain etc. For an acoustic event classification task containing 61 distinct classes, classification accuracy of the neural network classifier (60.3%) excels that of the conventional Gaussian mixture model based hidden Markov model classifier (54.8%). In addition, an unsupervised layer-wise pretraining followed by standard backpropagation training of a deep network (known as a deep belief network) results in further increase of 2-4% in classification accuracy. Effects of implementation parameters such as types of features and number of adjacent frames as additional features are found to be significant on classification accuracy.","PeriodicalId":198408,"journal":{"name":"2014 22nd European Signal Processing Conference (EUSIPCO)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2014-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"109","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2014 22nd European Signal Processing Conference (EUSIPCO)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5281/ZENODO.43987","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 109

Abstract

This paper proposes the use of a deep neural network for the recognition of isolated acoustic events such as footsteps, baby crying, motorcycle, rain etc. For an acoustic event classification task containing 61 distinct classes, classification accuracy of the neural network classifier (60.3%) excels that of the conventional Gaussian mixture model based hidden Markov model classifier (54.8%). In addition, an unsupervised layer-wise pretraining followed by standard backpropagation training of a deep network (known as a deep belief network) results in further increase of 2-4% in classification accuracy. Effects of implementation parameters such as types of features and number of adjacent frames as additional features are found to be significant on classification accuracy.
基于深度神经网络的声学事件识别
本文提出使用深度神经网络来识别孤立的声音事件,如脚步声、婴儿哭声、摩托车、雨水等。对于包含61个不同类别的声学事件分类任务,神经网络分类器的分类准确率(60.3%)优于基于高斯混合模型的隐马尔可夫模型分类器(54.8%)。此外,在深度网络(称为深度信念网络)的标准反向传播训练之后进行无监督分层预训练,分类精度进一步提高了2-4%。实现参数(如特征类型和相邻帧的数量作为附加特征)对分类精度的影响是显著的。
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:481959085
Book学术官方微信