arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.01436eess.AScs.SD
收藏

WaveBeat:时域中的端到端节拍和下拍跟踪

WaveBeat: End-to-end beat and downbeat tracking in the time domain

Queen Mary University of London(伦敦玛丽女王大学)

Christian J. Steinmetz, Joshua D. Reiss

摘要:

用于节拍和强拍跟踪的深度学习方法带来了进步。然而,这些方法仍然依赖于手工制作的、二次采样的光谱特征作为输入,限制了模型可用的信息。在这项工作中,我们提出了WaveBeat,一种端到端的方法,用于直接在波形上进行联合节拍和下拍跟踪。这种方法放弃了工程频谱特征,而是直接从波形中产生节拍和下拍预测,这是该任务的第一种。我们的模型利用时间卷积网络(TCN)的波形,实现了一个非常大的感受野($\geq$ 30秒)在音频采样率在内存有效的方式,通过采用快速增长的膨胀因子与较少的层。通过简单的数据增强策略,我们的方法在某些数据集上优于以前的最先进方法,同时在其他数据集上产生可比的结果,证明了时域方法的潜力。

英文摘要:

Deep learning approaches for beat and downbeat tracking have brought advancements. However, these approaches continue to rely on hand-crafted, subsampled spectral features as input, restricting the information available to the model. In this work, we propose WaveBeat, an end-to-end approach for joint beat and downbeat tracking operating directly on waveforms. This method forgoes engineered spectral features, and instead, produces beat and downbeat predictions directly from the waveform, the first of its kind for this task. Our model utilizes temporal convolutional networks (TCNs) operating on waveforms that achieve a very large receptive field ($\geq$ 30 s) at audio sample rates in a memory efficient manner by employing rapidly growing dilation factors with fewer layers. With a straightforward data augmentation strategy, our method outperforms previous state-of-the-art methods on some datasets, while producing comparable results on others, demonstrating the potential for time domain approaches.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑