UNIGE document Scientific Article
previous document  unige:93926  next document
add to browser collection
Title

Developing a benchmark for emotional analysis of music

Authors
Yang, Yi-Hsuan
Published in PLOS ONE. 2017, vol. 12, no. 3, p. e0173392
Abstract Music emotion recognition (MER) field rapidly expanded in the last decade. Many new methods and new audio features are developed to improve the performance of MER algorithms. However, it is very difficult to compare the performance of the new methods because of the data representation diversity and scarcity of publicly available data. In this paper, we address these problems by creating a data set and a benchmark for MER. The data set that we release, a MediaEval Database for Emotional Analysis in Music (DEAM), is the largest available data set of dynamic annotations (valence and arousal annotations for 1,802 songs and song excerpts licensed under Creative Commons with 2Hz time resolution). Using DEAM, we organized the ‘Emotion in Music' task at MediaEval Multimedia Evaluation Campaign from 2013 to 2015. The benchmark attracted, in total, 21 active teams to participate in the challenge. We analyze the results of the benchmark: the winning algorithms and feature-sets. We also describe the design of the benchmark, the evaluation procedures and the data cleaning and transformations that we suggest. The results from the benchmark suggest that the recurrent neural network based approaches combined with large feature-sets work best for dynamic MER.
Keywords EmotionsAlgorithmsMachine learning algorithmsNeural networksAcousticsMusic perceptionLinear regression analysis
Identifiers
Full text
Structures
Research groups Affective sciences
Computer Vision and Multimedia Laboratory
Multimodal Interaction Group
Project FNS: Ambizione
Citation
(ISO format)
ALJANAKI, Anna, YANG, Yi-Hsuan, SOLEYMANI, Mohammad. Developing a benchmark for emotional analysis of music. In: PLOS ONE, 2017, vol. 12, n° 3, p. e0173392. https://archive-ouverte.unige.ch/unige:93926

116 hits

64 downloads

Update

Deposited on : 2017-05-02

Export document
Format :
Citation style :