SampleCNN: End-to-End Deep Convolutional Neural Networks Using Very Small Filters for Music Classification

Applied Sciences

Keunhyoung Luke Kim¹  Jongpil Lee¹  Jiyoung Park¹  Juhan Nam¹ 

[1] Graduate School of Culture Technology, KAIST, 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Korea;

关键词: convolutional neural networks;    music classification;    raw waveforms;    sample-level filters;    downsampling;    filter visualization;    transfer learning;   

DOI  :  10.3390/app8010150

来源: DOAJ

【 摘 要 】

Convolutional Neural Networks (CNN) have been applied to diverse machine learning tasks for different modalities of raw data in an end-to-end fashion. In the audio domain, a raw waveform-based approach has been explored to directly learn hierarchical characteristics of audio. However, the majority of previous studies have limited their model capacity by taking a frame-level structure similar to short-time Fourier transforms. We previously proposed a CNN architecture which learns representations using sample-level filters beyond typical frame-level input representations. The architecture showed comparable performance to the spectrogram-based CNN model in music auto-tagging. In this paper, we extend the previous work in three ways. First, considering the sample-level model requires much longer training time, we progressively downsample the input signals and examine how it affects the performance. Second, we extend the model using multi-level and multi-scale feature aggregation technique and subsequently conduct transfer learning for several music classification tasks. Finally, we visualize filters learned by the sample-level CNN in each layer to identify hierarchically learned features and show that they are sensitive to log-scaled frequency.

【 授权许可】

Unknown