Show simple item record

dc.contributor.author杨武夷
dc.contributor.author孙馨喆
dc.contributor.author张宇
dc.contributor.author魏翀
dc.contributor.author杨燕明
dc.contributor.author牛富强
dc.date.accessioned2018-11-26T07:24:17Z
dc.date.available2018-11-26T07:24:17Z
dc.date.issued2016-03-15
dc.identifier.citation声学学报,2016,41(02):39-46
dc.identifier.issn0371-0025
dc.identifier.otherXIBA201602005
dc.identifier.urihttps://dspace.xmu.edu.cn/handle/2288/162547
dc.description.abstract针对宽吻海豚通讯信号自动分类提出了一种基于句法模式识别的方法。该方法首先提取海豚通讯信号基频随时间变化的轨迹曲线,然后提取基频变化的基元序列。根据海豚通讯信号分类的标准,归纳出产生各类海豚通讯信号基频基元序列的文法。对未知类别的海豚通讯信号,提取其基频变化的基元序列,根据各类模式的文法对基元序列进行分类,进而实现海豚通讯信号的自动分类。实验结果显示本文方法的分类准确率达到了95%。本文方法预期为海豚生物学行为的声学研究提供一定的技术支持。
dc.description.abstractTo automatically classify bottlenose dolphin's whistles,a method,which is based on syntactic pattern recognition,is presented.Dolphin whistles have typically been characterized in terms of their instantaneous frequency as a function of time,which is also known as "whistle contour".The frequency variation feature of a dolphin whistle is extracted according to its whistle contour.Then,the frequency variation features are used for learning grammatical patterns.A dolphin whistle is classified according to grammatical pattern of its frequency variation feature.Experimental results show that the classification accuracy of the proposed method is 95%.The method can provide technical support for acoustic study of dolphins' biological behavior.
dc.language.isozh_CN
dc.title一种宽吻海豚通讯信号自动分类的方法
dc.title.alternativeAn automatic classification method for whistles of bottlenose dolphin(Tursiops truncates)
dc.typeArticle


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record