Automated Classification of Dugong Calls and Tonal Noise by Combining Contour and MFCC Features

IF 1.7 4区 物理与天体物理 Acoustics Australia Pub Date : 2021-04-10 DOI:10.1007/s40857-021-00234-5
Kotaro Tanaka, Kotaro Ichikawa, Kongkiat Kittiwattanawong, Nobuaki Arai, Hiromichi Mitamura
{"title":"Automated Classification of Dugong Calls and Tonal Noise by Combining Contour and MFCC Features","authors":"Kotaro Tanaka,&nbsp;Kotaro Ichikawa,&nbsp;Kongkiat Kittiwattanawong,&nbsp;Nobuaki Arai,&nbsp;Hiromichi Mitamura","doi":"10.1007/s40857-021-00234-5","DOIUrl":null,"url":null,"abstract":"<div><p>To expand the spatial and temporal scales of passive acoustic monitoring of animals, automatically detecting target sounds among noises with similar acoustic properties is essential but challenging. In particular, the classification of tonal vocalisations and tonal noise remains a universal problem in bioacoustics research. The vocalisations of dugong, which is an endangered marine mammal that inhabits coastal seas, need to be monitored to enhance our understanding of its habitat use. However, detecting dugong tonal vocalisations is difficult due to the presence of tonal noise in the same frequency band. In this study, a classification method was developed for these signals to handle large acoustic data by reducing the labour required for manual inspection. Mel-frequency cepstral coefficients (MFCC) were extracted to characterise background sounds along with a few parameters of the signal contour, and a support vector machine was trained for binary classification. The classifier achieved an 84.4% recall and a 93.5% precision on the testing dataset even in a noisy shallow marine environment. This methodology enables the effective classification of dugong calls and similar tonal noises by combining contour and MFCC features and can extend the spatial and temporal scale of acoustic monitoring of the endangered dugong. This technique is potentially applicable to the monitoring of other endangered marine mammals that produce tonal vocalisations.</p></div>","PeriodicalId":54355,"journal":{"name":"Acoustics Australia","volume":"49 2","pages":"385 - 394"},"PeriodicalIF":1.7000,"publicationDate":"2021-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1007/s40857-021-00234-5","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Acoustics Australia","FirstCategoryId":"101","ListUrlMain":"https://link.springer.com/article/10.1007/s40857-021-00234-5","RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

To expand the spatial and temporal scales of passive acoustic monitoring of animals, automatically detecting target sounds among noises with similar acoustic properties is essential but challenging. In particular, the classification of tonal vocalisations and tonal noise remains a universal problem in bioacoustics research. The vocalisations of dugong, which is an endangered marine mammal that inhabits coastal seas, need to be monitored to enhance our understanding of its habitat use. However, detecting dugong tonal vocalisations is difficult due to the presence of tonal noise in the same frequency band. In this study, a classification method was developed for these signals to handle large acoustic data by reducing the labour required for manual inspection. Mel-frequency cepstral coefficients (MFCC) were extracted to characterise background sounds along with a few parameters of the signal contour, and a support vector machine was trained for binary classification. The classifier achieved an 84.4% recall and a 93.5% precision on the testing dataset even in a noisy shallow marine environment. This methodology enables the effective classification of dugong calls and similar tonal noises by combining contour and MFCC features and can extend the spatial and temporal scale of acoustic monitoring of the endangered dugong. This technique is potentially applicable to the monitoring of other endangered marine mammals that produce tonal vocalisations.

Abstract Image

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
结合轮廓和MFCC特征的儒艮叫声和音调噪声自动分类
为了扩大动物被动声监测的空间和时间尺度,在具有相似声学特性的噪声中自动检测目标声音是必不可少的,但也是具有挑战性的。特别是音调发声和音调噪声的分类一直是生物声学研究中的一个普遍问题。儒艮是一种生活在近海的濒危海洋哺乳动物,我们需要对其发声进行监测,以加深我们对其栖息地使用情况的了解。然而,由于在同一频带中存在音调噪声,检测儒艮的音调发声是困难的。在本研究中,开发了一种针对这些信号的分类方法,通过减少人工检查所需的劳动力来处理大量声学数据。提取Mel-frequency倒谱系数(MFCC)和一些信号轮廓参数来表征背景声音,并训练支持向量机进行二值分类。即使在嘈杂的浅海环境中,该分类器在测试数据集上也实现了84.4%的召回率和93.5%的精度。该方法结合轮廓线特征和MFCC特征,对儒艮叫声和相似音调噪声进行有效分类,扩展了濒危儒艮声学监测的时空尺度。这项技术可能适用于监测其他产生音调发声的濒危海洋哺乳动物。
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 去求助
来源期刊
Acoustics Australia
Acoustics Australia ACOUSTICS-
自引率
5.90%
发文量
24
期刊介绍: Acoustics Australia, the journal of the Australian Acoustical Society, has been publishing high quality research and technical papers in all areas of acoustics since commencement in 1972. The target audience for the journal includes both researchers and practitioners. It aims to publish papers and technical notes that are relevant to current acoustics and of interest to members of the Society. These include but are not limited to: Architectural and Building Acoustics, Environmental Noise, Underwater Acoustics, Engineering Noise and Vibration Control, Occupational Noise Management, Hearing, Musical Acoustics.
期刊最新文献
News Item Experimental Assessment of the Flow Recirculation Effect on the Noise Measurement of a Free-Flying Multi-rotor UAS in a Closed Anechoic Chamber Source Depth Discrimination Based on Interference Spectrum in Deep Water with an Incomplete Channel The Increasing Application of DIN 4150-3 for the Assessment of Potential Damage to Buildings from Construction Vibration and its Implications in Australia Towards an Acoustically Accessible Campus: A Case Study of the Acoustic Conditions of an Australian University
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1