arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.00200eess.AS
收藏

歌曲和语音情感识别的差异:特征集、特征类型和分类器的影响

On The Differences Between Song and Speech Emotion Recognition: Effect of Feature Sets, Feature Types, and Classifiers

Bagus Tris Atmaja, Masato Akagi

摘要:

在本文中,我们评估了不同的功能集,功能类型和分类器的歌曲和语音情感识别。三个功能集:GeMAPS,pyAudioAnalysis和LibROSA;两种特征类型:低级描述符和高级统计函数;以及四种分类器:多层感知器,LSTM,GRU和卷积神经网络在具有相同参数值的歌曲和语音数据上进行了检查。结果表明,使用相同的方法,歌曲和语音数据之间没有显着差异。此外,高层次的统计功能的声学特征获得了更高的性能分数比低层次的描述符在这个分类任务。这一结果加强了先前在回归任务中的发现,该任务报告了高级特征的优势使用。

英文摘要:

In this paper, we evaluate the different features sets, feature types, and classifiers on both song and speech emotion recognition. Three feature sets: GeMAPS, pyAudioAnalysis, and LibROSA; two feature types: low-level descriptors and high-level statistical functions; and four classifiers: multilayer perceptron, LSTM, GRU, and convolution neural networks are examined on both song and speech data with the same parameter values. The results show no remarkable difference between song and speech data using the same method. In addition, high-level statistical functions of acoustic features gained higher performance scores than low-level descriptors in this classification task. This result strengthens the previous finding on the regression task which reported the advantage use of high-level features.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑