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 |
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。
修改评论