Automatic Music Stretching Resistance Classification Using Audio Features and Genres
Automatic Music Stretching Resistance Classification Using Audio Features and Genres
复制标题
使用音频特征和流派自动音乐拉伸阻力分类
DOI：
10.1109/lsp.2013.2286200
复制
发表时间：
2013-12-01
影响因子：
3.9
通讯作者：
Wang, Chaokun
中科院分区：
文献类型：
--
作者：
Chen, Jun;Wang, Chaokun
音乐拉伸阻力（Music Stretching Resistance，MSR）是音频信号处理中一个新的重要概念，它表征了音乐作品在时间上被拉伸（压缩或拉长）而没有令人反感的感知伪影的能力。它有可能在各种多媒体应用中被高度要求，如音乐播放，音频编辑和多媒体集成，但在文献中几乎没有关于音乐的这种属性的先验知识。在这封信中，MSR的任务制定的第一次，并MSR分类方法，采用度量学习的音频特征和类型也被提出。它试图自动化人类可接受的音乐时间拉伸率范围应该是什么。在对比实验中，该方法在准确率上优于参考分类方法。
Music stretching resistance (MSR) is a fresh but important concept in audio signal processing, which characterizes the ability of a music piece to be stretched in time (compressed or elongated) without objectionable perceptual artifacts. It has the potential to be highly demanded in various multimedia applications like music resizing, audio editing and multimedia integration, but there is almost no prior knowledge about this property of music in literature. In this letter, the task of MSR is formulated for the first time, and an MSR classification method that employs metric learning on audio features and genres is also proposed. It attempts to automate what human acceptable time-stretching rate range of music should be. The proposed method outperforms the reference classification methods in accuracy in the comparative experiments.