用自监督音频嵌入提升音乐流派分类，BYOL-A表现最佳。
Evaluating Pretrained General-Purpose Audio Representations for Music Genre Classification
- 采用BYOL-A音频嵌入+深度神经网络分类器
- 在GTZAN上达81.5%准确率，比线性分类器高10-16%
- 支持跨数据集训练，代码开源可复现
本研究探讨了自监督学习嵌入（特别是BYOL-A）与深度神经网络分类器结合用于音乐流派分类的效果。实验表明，BYOL-A嵌入优于PANNs和VGGish等预训练模型，在GTZAN数据集上达到81.5%的准确率，在FMA-Small上达64.3%。所提出的DNN分类器相比线性分类器性能提升10-16%。研究还探索了对比损失与三元组损失及多任务训练，通过优化损失权重获得最高准确率。为应对跨数据集挑战，将GTZAN与FMA-Small合并为统一的18类标签空间进行联合训练，导致GTZAN性能略有下降，但FMA-Small结果保持相当。本文开发的脚本已公开。
原文摘要 · Abstract (English)
This study investigates the use of self-supervised learning embeddings, particularly BYOL-A, in conjunction with a deep neural network classifier for Music Genre Classification. Our experiments demonstrate that BYOL-A embeddings outperform other pre-trained models, such as PANNs and VGGish, achieving an accuracy of 81.5% on the GTZAN dataset and 64.3% on FMA-Small. The proposed DNN classifier improved performance by 10-16% over linear classifiers. We explore the effects of contrastive and triplet loss and multitask training with optimized loss weights, achieving the highest accuracy. To address cross dataset challenges, we combined GTZAN and FMA-Small into a unified 18-class label space for joint training, resulting in slight performance drops on GTZAN but comparable results on FMA-Small. The scripts developed in this work are publicly available.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。