BriefGPT.xyz
Dec, 2022
MAP-Music2Vec：自监督音乐音频表示学习的简单有效基准
MAP-Music2Vec: A Simple and Effective Baseline for Self-Supervised Music Audio Representation Learning
HTML
PDF
Yizhi Li, Ruibin Yuan, Ge Zhang, Yinghao Ma, Chenghua Lin...
TL;DR
Music2Vec是一种基于自监督学习算法的音乐原始波形有用特征表示学习的框架，参数数量大幅少于现有的音乐自监督学习框架，但表现与现有最优解相当，该模型将在Huggingface发布。
Abstract
The
deep learning
community has witnessed an exponentially growing interest in
self-supervised learning
(
ssl
). However, it still remains u
→