文章摘要
李晗,陈克安,田旭华.基于平板冲击声的声源特性表征及自动识别*[J].,2016,35(4):294-301
基于平板冲击声的声源特性表征及自动识别*
Characterization of sound source physical properties and automatic identification based on impact sounds of plates *
投稿时间:2015-10-11  修订日期:2016-06-25
中文摘要:
      以平板结构导纳函数为纽带,建立冲击声信号特征与声源特性之间的关联,获得对声源特性更细致的描述,从而实现声源的有效辨识。针对四边简支矩形被击板,借助信号参数识别算法获得与声源物理属性有关的6维导纳特征,并从冲击声样本中提取80维音色特征,将音色特征和导纳特征做相关性分析,获得与声源物理属性相关的信号特征集。利用BP神经网络进行分类,结果表明,当采用与特定声源物理属性相关的信号特征子集时,分类效果达到同组最优。
英文摘要:
      Regarding the mobility of impact plates as a link, the relationship between the acoustic features and the physical properties of the sources is constructed, and more detailed description of the sound sources is acquired and more effective sound source recognition is achieved. Aiming at a simply supported rectangular plate, through modal identification techniques, six mobility features associated with physical properties are obtained. Timbre features with 80 dimensions are extracted from impact sounds. Through the correlation analysis of the acoustic features and the mobility features, a subset of acoustic feature is acquired relating to sound source properties. Then the sound source identification is conducted through the BP neural network. When using the feature subset associated with mobility features, the identification become best in the same group.
DOI:10.11684/j.issn.1000-310X.2016.04.003
中文关键词: 声源特性,导纳特征,特征提取
英文关键词: Sound source property, Mobility features, Feature extraction
基金项目:(11574249);国家自然科学基金项目(面上项目,重点项目,重大项目);航空科学基金(20131553018)
作者单位E-mail
李晗 西北工业大学航海学院 西安 710072 lihan@mail.nwpu.edu.cn 
陈克安 西北工业大学航海学院 西安 710072 kachen@nwpu.edu.cn 
田旭华 西北工业大学航海学院 西安 710072 txh3093@sina.com 
摘要点击次数: 1621
全文下载次数: 873
查看全文   查看/发表评论  下载PDF阅读器
关闭