文章摘要
宿元亮,刘志红,王万凯,赵玉贵,仪垂杰.流形学习在运动声源声特征提取方面的研究*[J].,2019,38(6):961-968
流形学习在运动声源声特征提取方面的研究*
Research on manifold learning in acoustic feature extraction of moving sound source
投稿时间:2019-02-16  修订日期:2019-10-30
中文摘要:
      运动声源因声信号时变性、叠加性和空时耦合性强,声数据呈现高维、非线性等特点,使得关键声特征提取困难,声特征提取方法复杂度高、数值计算量大、有效性差。因此,如何有效提取声特征并降低提取方法复杂度成为目前多源声场声源精准识别迫切解决的关键科学问题。由此,本文提出短时傅里叶变换(STFT)和局部线性嵌入算法(LLE)联合的STFT-LLE流形学习声特征提取方法,并将此方法应用于运动声特征提取,且通过仿真实验测试对其进行了验证。
英文摘要:
      Moving noise is characterized by time-varying, superimposing and space-time coupling of sound signals, and the sound data is characterized by high dimensionality and nonlinearity, which makes it difficult to extract key acoustic features. The method of sound feature extraction has high complexity, large numerical calculation and poor validity. Therefore, how to effectively extract acoustic features and reduce the complexity of the extraction method has become an important scientific problem for the accurate identification of multi-source acoustic sources. In this paper, the STFT-LLE manifold learning method is proposed. It combined with short-time Fourier transform (STFT) and local linear embedding algorithm (LLE).This method is applied to the feature extraction of motion acousticfield. It is validated by simulation experiments.
DOI:10.11684/j.issn.1000-310X.2019.06.008
中文关键词: 运动声源,特征提取,流形学习,短时傅里叶变换,局部线性嵌入,
英文关键词: Moving sound source, Feature  extraction, Manifold  learning, Short  time Fourier  transform, Locally  linear embedding
基金项目:(61671262)、(61871447 )
作者单位E-mail
宿元亮 青岛理工大学 机械与汽车工程学院 359079564@qq.com 
刘志红 青岛理工大学机械与汽车工程学院 470603475@qq.com 
王万凯 青岛理工大学机械与汽车工程学院 308487024@qq.com 
赵玉贵 青岛理工大学机械与汽车工程学院 2654385851@qq.com 
仪垂杰* 工业流体节能与污染控制教育部重点实验室 青岛 chuijieyi@vip.163.com 
摘要点击次数: 1483
全文下载次数: 847
查看全文   查看/发表评论  下载PDF阅读器
关闭