A separate and restore approach to score-informed music decomposition
A separate and restore approach to score-informed music decomposition
复制标题
DOI：
10.1109/waspaa.2015.7336883
复制
发表时间：
2015-10
期刊：
影响因子：
--
通讯作者：
C. Dittmar;Jonathan Driedger;Meinard Müller
中科院分区：
文献类型：
--
作者：
C. Dittmar;Jonathan Driedger;Meinard Müller
我们的目标是提高音乐源分离的背景下提取的信号分量的感知质量。具体来说，我们专注于分解复调，单音色钢琴录音到声音事件，对应于潜在的组成的各个音符。我们的分离技术是基于分数通知的非负矩阵分解（NMF），已被提出在早期的作品作为一种有效的手段，以执行一个音乐上有意义的钢琴音乐分解。然而，该方法仍然有一定的缺点，复杂的混合物中的音调强烈重叠的频率和时间。作为本文的主要贡献，我们提出了一个恢复阶段的基础上改进的维纳滤波器面具得分通知NMF。我们的想法是引入从完全孤立的钢琴音调的字典中创建的音符软面具，然后调整以匹配目标组件的音色。钢琴音调的混合物的基本实验表明，我们的新的重建方法在感知动机的分离质量指标方面的改进。第二个实验更复杂的钢琴录音表明，进一步调查的概念是必要的现实世界的适用性。
Our goal is to improve the perceptual quality of signal components extracted in the context of music source separation. Specifically, we focus on decomposing polyphonic, mono-timbral piano recordings into the sound events that correspond to the individual notes of the underlying composition. Our separation technique is based on score-informed Non-Negative Matrix Factorization (NMF) that has been proposed in earlier works as an effective means to enforce a musically meaningful decomposition of piano music. However, the method still has certain shortcomings for complex mixtures where the tones strongly overlap in frequency and time. As the main contribution of this paper, we propose a restoration stage based on refined Wiener filter masks to score-informed NMF. Our idea is to introduce notewise soft masks created from a dictionary of perfectly isolated piano tones, which are then adapted to match the timbre of the target components. A basic experiment with mixtures of piano tones shows improvements of our novel reconstruction method with regard to perceptually motivated separation quality metrics. A second experiment with more complex piano recordings shows that further investigations into the concept are necessary for real-world applicability.