Beat Tracking using Recurrent Neural Network: A Transfer Learning Approach
Beat Tracking using Recurrent Neural Network: A Transfer Learning Approach
复制标题
使用循环神经网络进行节拍跟踪：一种迁移学习方法
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
A. Sarti
中科院分区：
文献类型：
--
作者：
D. Fiocchi;Michele Buccoli;M. Zanoni;F. Antonacci;A. Sarti
深度学习网络已经被成功地应用于解决大量的任务。深度学习网络的有效性受到用于训练的数据量和种类的限制。因此，深度学习网络可以应用于海量数据可用的场景。在音乐信息检索中，由于注释音乐片段的可获得性更广，这是流行流派的情况。相反，对于不广为流传的流派来说，找到足够和有用的数据是一项艰巨的任务，比如传统音乐和民间音乐。为了解决这个问题，转移学习被提出，即使用大量可用的数据集来训练网络，然后将学习到的知识(分层表示)转移到另一个任务。在这项工作中，我们提出了一种将迁移学习应用于节拍跟踪的方法。我们使用一个基于深度BLSTM的RNN作为训练流行音乐的起始网络，并将其转移到跟踪希腊民间音乐的节拍。为了评估我们的方法的有效性，我们收集了一个希腊民间音乐的数据集，并对这些片段进行了手动标注。
Deep learning networks have been successfully applied to solve a large number of tasks. The effectiveness of deep learning networks is limited by the amount and the variety of data used for the training. For this reason, deep-learning networks can be applied in scenarios where a huge amount of data are available. In music information retrieval, this is the case of popular genres due to the wider availability of annotated music pieces. Instead, to find sufficient and useful data is a hard task for non widespread genres, like, for instance, traditional and folk music. To address this issue, Transfer Learning has been proposed, i.e., to train a network using a large available dataset and then transfer the learned knowledge (the hierarchical representation) to another task. In this work, we propose an approach to apply transfer learning for beat tracking. We use a deep BLSTM-based RNN as the starting network trained on popular music, and we transfer it to track beats of Greek folk music. In order to evaluate the effectiveness of our approach, we collect a dataset of Greek folk music, and we manually annotate the pieces.