Musical source separation
Musical source separation
复制标题
音源分离
DOI：
--
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
A. Mocanu
中科院分区：
文献类型：
--
作者：
A. Mocanu
音乐源分离是一个复杂的主题，在信号处理领域得到了广泛的探索，并从最近的机器学习研究中受益匪浅。在过去的几年里，已经发布了许多具有令人印象深刻的源分离质量的深度学习模型，所有这些模型都处理工作室录制的音乐，分为四种乐器类别，人声，鼓，贝斯和其他。我们研究了如何扩大乐器类别的数量，并得出结论，电吉他也是可行的分离。然后，我们将注意力转向使用参数化滤波器组学习相关的信号编码，我们观察到滤波器组不能单独改进简单卷积，但如果编码器由卷积和滤波器组组成，则可以提供帮助。最后，我们尝试将在工作室音乐上训练的模型适应于现场音乐分离，并得出结论，在干净数据上训练的模型也能在现场音乐上提供最佳表现。
Musical source separation is a complex topic that has been extensively explored in the signal processing community and has benefited greatly from recent machine learning research. Many deep learning models with impressive source separation quality have been released in the last couple of years, all of them dealing with studio recorded music split into four instrument categories, vocals, drums, bass and other. We study how we can extend the number of instrument categories and conclude that electric guitar is also feasible to separate. We then turn our attention towards learning relevant signal encodings using parameterized filterbanks and we observe that filterbanks can not improve over simple convolutions on their own, but can help if the encoder is composed of both convolutions and filterbanks. Finally, we try to adapt models trained on studio music to live music separation and conclude that models trained on clean data also provide the best performance on live music as well.
影响因子：
14.9
作者：
Sebastian Ewert;Bryan Pardo;Meinard Müller;Mark D. Plumbley
通讯作者：
Sebastian Ewert;Bryan Pardo;Meinard Müller;Mark D. Plumbley