CORC  > 兰州理工大学  > 兰州理工大学
Repeating patttern discovery of audio
Du, ZL; Li, XL; Wang, T; Wang, LX
2005
关键词audio feature spectrogram frame discernibility
页码1806-1811
英文摘要In this paper, we propose an effective method to discover repeating pattern from audio. Since the previous feature extraction methods are usually process monophony audio, for extracting more descriptive features from polyphony audio, Gabor filters bank is introduced. Meanwhile the measure criteria is given for qualitatively and quantitatively weighting the discernibility of extracted features. In addition, we present an incremental repeating pattern discovering algorithm with time complexity O(nlog(n)). Experimental evaluations show that our proposed method could extract complete and meaningful repeating patterns from polyphony audio.
会议录PROCEEDINGS OF 2005 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-9
会议录出版者IEEE
会议录出版地345 E 47TH ST, NEW YORK, NY 10017 USA
语种英语
WOS研究方向Computer Science
WOS记录号WOS:000235325602089
内容类型会议论文
源URL[http://119.78.100.223/handle/2XXMBERH/38305]  
专题兰州理工大学
通讯作者Du, ZL
作者单位Lanzhou Univ Technol, Sch Comp & Commun, Lanzhou 730050, Peoples R China
推荐引用方式
GB/T 7714
Du, ZL,Li, XL,Wang, T,et al. Repeating patttern discovery of audio[C]. 见:.
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace