当前位置: X-MOL 学术Music Perception › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Challenges and Opportunities of Predicting Musical Emotions with Perceptual and Automatized Features
Music Perception ( IF 2.184 ) Pub Date : 2018-12-01 , DOI: 10.1525/mp.2018.36.2.217
Elke B. Lange 1 , Klaus Frieler 2
Affiliation  

Music information retrieval (MIR) is a fast-growing research area. One of its aims is to extract musical characteristics from audio. In this study, we assumed the roles of researchers without further technical MIR experience and set out to test in an exploratory way its opportunities and challenges in the specific context of musical emotion perception. Twenty sound engineers rated 60 musical excerpts from a broad range of styles with respect to 22 spectral, musical, and cross-modal features ( perceptual features ) and perceived emotional expression. In addition, we extracted 86 features ( acoustic features ) of the excerpts with the MIRtoolbox (Lartillot & Toiviainen, 2007). First, we evaluated the perceptual and extracted acoustic features. Both perceptual and acoustic features posed statistical challenges (e.g., perceptual features were often bimodally distributed, and acoustic features highly correlated). Second, we tested the suitability of the acoustic features for modeling perceived emotional content. Four nearly disjunctive feature sets provided similar results, implying a certain arbitrariness of feature selection. We compared the predictive power of perceptual and acoustic features using linear mixed effects models, but the results were inconclusive. We discuss critical points and make suggestions to further evaluate MIR tools for modeling music perception and processing.

中文翻译:

具有感知和自动化功能的音乐情感预测的挑战与机遇

音乐信息检索(MIR)是一个快速发展的研究领域。其目的之一是从音频中提取音乐特征。在这项研究中,我们假设没有进一步的技术MIR经验的研究人员的角色,并着手以探索性的方式测试其在音乐情感感知中的机遇和挑战。二十位音响工程师从22种频谱,音乐和跨模态特征(感知特征)和感知到的情感表达方面,对来自各种风格的60个音乐摘录进行了评分。此外,我们使用MIRtoolbox提取了摘录的86个特征(声学特征)(Lartillot和Toiviainen,2007)。首先,我们评估了感知和提取的声学特征。感知和听觉特征都构成统计挑战(例如,感知特征通常是双峰分布的,并且声学特征高度相关)。其次,我们测试了声学特征对感知情感内容建模的适用性。四个近乎分离的特征集提供了相似的结果,这意味着特征选择具有一定的任意性。我们使用线性混合效应模型比较了感知和声学特征的预测能力,但结果尚无定论。我们讨论关键点并提出建议,以进一步评估用于对音乐感知和处理进行建模的MIR工具。暗示了特征选择的一定随意性。我们使用线性混合效应模型比较了感知和声学特征的预测能力,但结果尚无定论。我们讨论关键点并提出建议,以进一步评估用于对音乐感知和处理进行建模的MIR工具。暗示了特征选择的一定随意性。我们使用线性混合效应模型比较了感知和声学特征的预测能力,但结果尚无定论。我们讨论关键点并提出建议,以进一步评估用于对音乐感知和处理进行建模的MIR工具。
更新日期:2018-12-01
down
wechat
bug