A Feature Survey for Emotion Classification of Western Popular Music
A Feature Survey for Emotion Classification of Western Popular Music
复制标题
DOI：
--
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
Scott Beveridge;Don Knox
中科院分区：
文献类型：
--
作者：
Scott Beveridge;Don Knox
本文提出了一种用于西方流行音乐情感分类的特征集。通过研究一系列常见的特征提取方法，我们证明了一组5个特征可以很好地建模情感。为了对系统进行评估，我们实现了一个旨在测试系统泛化性的独立特征评估范式；机器学习算法在不同数据集上保持良好性能的能力。
In this paper we propose a feature set for emotion classifi- cation of Western popular music. We show that by surveying a range of common feature extraction methods, a set of five features can model emotion with good accuracy. To evaluate the system we implement an in- dependent feature evaluation paradigm aimed at testing the property of generalizability; the ability of a machine learning algorithm to maintain good performance over different data sets.