【24h】

Problems with Automatic Classification of Musical Sounds

机译:音乐声音自动分类的问题

获取原文
获取外文期刊封面目录资料

摘要

Convenient searching of multimedia databases requires well annotated data. Labeling sound data with information like pitch or timbre must be done through sound analysis. In this paper, we deal with the problem of automatic classification of musical instrument on the basis of its sound. Although there are algorithms for basic sound descriptors extraction, correct identification of instrument still poses a problem. We describe difficulties encountered when classifying woodwinds, brass, and strings of contemporary orchestra. We discuss most difficult cases and explain why these sounds cause problems. The conclusions are drawn and presented in brief summary closing the paper.
机译:方便地搜索多媒体数据库需要带有注释的数据。必须通过声音分析对带有声音或音色等信息的声音数据进行标记。在本文中,我们基于乐器的声音来处理乐器的自动分类问题。尽管有用于提取基本声音描述符的算法,但是正确识别乐器仍然存在问题。我们描述了在对木管乐器,铜管乐器和现代管弦乐队进行分类时遇到的困难。我们讨论最困难的情况,并解释为什么这些声音会引起问题。得出结论,并在结束本文时作简要总结。

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