Multi-Level and Multi-Scale Feature Aggregation Using Sample-level Deep Convolutional Neural Networks for Music Classification

TL;DR

This paper introduces a novel music classification method that leverages multi-level and multi-scale feature aggregation from sample-level deep CNNs trained on raw waveforms, achieving state-of-the-art results.

Contribution

It proposes a new approach combining multi-level and multi-scale feature aggregation with pre-trained sample-level deep CNNs for improved music classification.

Findings

Achieves state-of-the-art results on multiple datasets

Effectively captures multi-level and multi-scale features

Demonstrates the effectiveness of raw waveform-based CNNs

Abstract

Music tag words that describe music audio by text have different levels of abstraction. Taking this issue into account, we propose a music classification approach that aggregates multi-level and multi-scale features using pre-trained feature extractors. In particular, the feature extractors are trained in sample-level deep convolutional neural networks using raw waveforms. We show that this approach achieves state-of-the-art results on several music classification datasets.