MDCNN-SID：用于Singer识别的多尺度扩张卷积网络
MDCNN-SID: Multi-scale Dilated Convolution Network for Singer Identification
摘要：
大多数歌手识别方法都是在频域中处理的，这可能导致频谱变换过程中的信息丢失。在本文中，而不是频域，我们提出了一个端到端的架构，解决这个问题的波形域。介绍了一种基于多尺度扩张卷积神经网络（MDCNN）的编码器，用于从原始音频信号中生成波形嵌入。具体地说，在所提出的方法中使用膨胀卷积层来扩大感受野，旨在提取歌曲级特征。此外，主干网中的跳跃连接集成了通过卷积层的堆叠学习的多分辨率声学特征。然后，将获得的波嵌入传递到下面的网络中进行歌手识别。在Artist20基准数据集上的实验结果表明，该方法具有相当的性能，显著提高了相关工作的效率。
英文摘要：
Most singer identification methods are processed in the frequency domain, which potentially leads to information loss during the spectral transformation. In this paper, instead of the frequency domain, we propose an end-to-end architecture that addresses this problem in the waveform domain. An encoder based on Multi-scale Dilated Convolution Neural Networks (MDCNN) was introduced to generate wave embedding from the raw audio signal. Specifically, dilated convolution layers are used in the proposed method to enlarge the receptive field, aiming to extract song-level features. Furthermore, skip connection in the backbone network integrates the multi-resolution acoustic features learned by the stack of convolution layers. Then, the obtained wave embedding is passed into the following networks for singer identification. In experiments, the proposed method achieves comparable performance on the benchmark dataset of Artist20, which significantly improves related works.
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。
