Multi-Task Learning of Tempo and Beat: Learning One to Improve the Other
Multi-Task Learning of Tempo and Beat: Learning One to Improve the Other
复制标题
节奏和节拍的多任务学习：学习其中一个以改进另一个
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Peter Knees
中科院分区：
文献类型：
--
作者：
Sebastian Böck;M. Davies;Peter Knees
提出了一种同时进行音乐音频节拍估计和节拍跟踪的多任务学习方法。该系统在广泛的数据上显示了这两个任务的最新性能，但还有另一个基本优势：由于其多任务性质，它不仅能够通过学习共同的、共享的表示来利用两个任务的相互信息，而且还可以通过仅从另一个任务中学习来提高一个任务的性能。多任务学习是通过全局聚合围绕时间卷积网络构建的节拍跟踪系统的跳跃连接，并将它们馈送到Tempo Classifi阳离子层来实现的。通过包括仅有节拍注释可用的训练数据来研究该方法的优点fit，并且这被证明在节拍跟踪精度方面提供了改进。
We propose a multi-task learning approach for simultaneous tempo estimation and beat tracking of musical audio. The system shows state-of-the-art performance for both tasks on a wide range of data, but has another fundamental advantage: due to its multi-task nature, it is not only able to exploit the mutual information of both tasks by learning a common, shared representation, but can also improve one by learning only from the other. The multi-task learning is achieved by globally aggregating the skip connections of a beat tracking system built around temporal convolutional networks, and feeding them into a tempo classification layer. The benefit of this approach is investigated by the inclusion of training data for which tempo-only annotations are available, and which is shown to provide improvements in beat tracking accuracy.
深度（呃）学习。
DOI：
10.1523/jneurosci.0153-18.2018
发表时间：
2018
期刊：
The Journal of neuroscience : the official journal of the Society for Neuroscience
影响因子：
--
作者：
Srinivasan,Shyam;Greenspan,RalphJ;Stevens,CharlesF;Grover,Dhruv
通讯作者：
Grover,Dhruv