首页> 外文期刊>Systems and Computers in Japan >Music Signal Spotting Retrieval by a Humming Query Using Model Driven Path Continuous Dynamic Program
【24h】

Music Signal Spotting Retrieval by a Humming Query Using Model Driven Path Continuous Dynamic Program

机译:使用模型驱动路径连续动态程序通过嗡嗡声查询检索音乐信号点

获取原文
获取原文并翻译 | 示例
       

摘要

In this paper the authors propose a search method for finding within various time series for acoustic analysis patterns for music the similar periods in a search query consisting of a time series of pitch differences (intervals) extracted from humming. The proposed method (model driven path Continuous Dynamic Programming) is an extension of continuous DP which allows for spotting searches and has the benefit of having the time series for the reference model directly identify the form of the slope limitations used in continuous DP. In this paper the authors perform humming query experiments for 20 songs of popular music and demonstrate the effectiveness of their proposed method.
机译:在本文中,作者提出了一种搜索方法,用于在音乐的声学分析模式的各个时间序列中找到由嗡嗡声提取的音高差异(间隔)时间序列组成的搜索查询中的相似时段。所提出的方法(模型驱动路径连续动态编程)是连续DP的扩展,它允许进行点搜索,并且具有使参考模型的时间序列直接识别连续DP中使用的斜率限制形式的好处。在本文中,作者对20首流行音乐进行嗡嗡声查询实验,并证明了所提方法的有效性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号