Music Genre Classification Using Transfer Learning

被引：6

作者：

Liang, Beici ^{[1
]}

Gu, Minwei ^{[1
]}

机构：

[1] Tencent Mus Entertainment, QQ Mus, Shenzhen, Peoples R China

来源：

THIRD INTERNATIONAL CONFERENCE ON MULTIMEDIA INFORMATION PROCESSING AND RETRIEVAL (MIPR 2020) | 2020年

关键词：

music genre classification; transfer learning;

D O I：

10.1109/MIPR49039.2020.00085

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

We proposed a transfer learning approach for audio-based classification of 11 western music genres, including Rock, Pop, Rap, Country, Folk, Metal, Jazz, Blues, R&B, Electronic Music and Classical Music. Multiple models were investigated. The best one can achieve 0.9799 ROC-AUC and 0.8938 PR-AUC on a private dataset of 1100 songs.

引用

页码：392 / 393

页数：2