Harmonic and Percussive Sound Separation and Its Application to MIR-Related Tasks
Harmonic and Percussive Sound Separation and Its Application to MIR-Related Tasks
复制标题
DOI：
10.1007/978-3-642-11674-2_10
复制
发表时间：
2010
期刊：
影响因子：
--
通讯作者：
Nobutaka Ono;Kenichi Miyamoto;H. Kameoka;Jonathan Le Roux;Yuuki Uchiyama;E. Tsunoo;T. Nishimoto;S. Sagayama
中科院分区：
文献类型：
--
作者：
Nobutaka Ono;Kenichi Miyamoto;H. Kameoka;Jonathan Le Roux;Yuuki Uchiyama;E. Tsunoo;T. Nishimoto;S. Sagayama
在本章中，我们提出了一种简单而快速的方法来将单声道音频信号分离为谐波分量和敲击分量，这为与MIR相关的任务提供了有用的预处理。利用谐波和冲击分量功率谱图的各向异性，定义了基于谱图梯度的目标函数，并对其应用辅助函数法，得到了保证目标函数在每次迭代时减小的简单而快速的更新方程。我们给出了流行音乐和爵士音乐的声音分离的实验结果，并给出了该技术在自动和弦识别和节奏模式提取中的应用。
In this chapter, we present a simple and fast method to separate a monaural audio signal into harmonic and percussive components, which leads to a useful pre-processing for MIR-related tasks. Exploiting the anisotropies of the power spectrograms of harmonic and percussive components, we define objective functions based on spectrogram gradients, and, applying to them the auxiliary function approach, we derive simple and fast update equations which guarantee the decrease of the objective function at each iteration. We show experimental results for sound separation on popular and jazz music pieces, and also present the application of the proposed technique to automatic chord recognition and rhythm-pattern extraction.