Developing a benchmark for emotional analysis of music - PubMed (original) (raw)
Developing a benchmark for emotional analysis of music
Anna Aljanaki et al. PLoS One. 2017.
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.
Conflict of interest statement
Competing Interests: The authors have declared that no competing interests exist.
Figures
Fig 1. A labyrinth of data representation choices for a MER algorithm.
The choices that we made for the benchmark are highlighted in red.
Fig 2. Annotation interface for both continuous (upper-left corner) and static per song (middle; using the self-assessment manikins [43]) ratings of arousal.
Fig 3. Fitted GAMs for the arousal and valence annotations of two songs.
Fig 4
Liking of the music and confidence in rating for a) valence, Spearman’s ρ = 0.37, _p_-value = 2.2 × 10−16 b) arousal, Spearman’s ρ = 0.29, _p_-value = 2.2 × 10−16.
Fig 5. Krippendorff’s α of dynamic annotations in 2015, averaged over all dynamic samples.
Fig 6
Distribution of the labels on arousal-valence plane for a) development-set b) evaluation-set.
Similar articles
- Using machine learning analysis to interpret the relationship between music emotion and lyric features.
Xu L, Sun Z, Wen X, Huang Z, Chao CJ, Xu L. Xu L, et al. PeerJ Comput Sci. 2021 Nov 15;7:e785. doi: 10.7717/peerj-cs.785. eCollection 2021. PeerJ Comput Sci. 2021. PMID: 34901433 Free PMC article. - MERP: A Music Dataset with Emotion Ratings and Raters' Profile Information.
Koh EY, Cheuk KW, Heung KY, Agres KR, Herremans D. Koh EY, et al. Sensors (Basel). 2022 Dec 29;23(1):382. doi: 10.3390/s23010382. Sensors (Basel). 2022. PMID: 36616980 Free PMC article. - Music-induced emotion flow modeling by ENMI Network.
Shang Y, Peng Q, Wu Z, Liu Y. Shang Y, et al. PLoS One. 2024 Oct 21;19(10):e0297712. doi: 10.1371/journal.pone.0297712. eCollection 2024. PLoS One. 2024. PMID: 39432493 Free PMC article. - A review: Music-emotion recognition and analysis based on EEG signals.
Cui X, Wu Y, Wu J, You Z, Xiahou J, Ouyang M. Cui X, et al. Front Neuroinform. 2022 Oct 25;16:997282. doi: 10.3389/fninf.2022.997282. eCollection 2022. Front Neuroinform. 2022. PMID: 36387584 Free PMC article. Review. - Music and emotions: from enchantment to entrainment.
Vuilleumier P, Trost W. Vuilleumier P, et al. Ann N Y Acad Sci. 2015 Mar;1337:212-22. doi: 10.1111/nyas.12676. Ann N Y Acad Sci. 2015. PMID: 25773637 Review.
Cited by
- A listener preference model for spatial sound reproduction, incorporating affective response.
Moiragias G, Mourjopoulos J. Moiragias G, et al. PLoS One. 2023 Jun 14;18(6):e0285135. doi: 10.1371/journal.pone.0285135. eCollection 2023. PLoS One. 2023. PMID: 37315025 Free PMC article. - Differential effects of familiarity and emotional expression of musical cues on autobiographical memory properties.
Jakubowski K, Francini E. Jakubowski K, et al. Q J Exp Psychol (Hove). 2023 Sep;76(9):2001-2016. doi: 10.1177/17470218221129793. Epub 2022 Oct 27. Q J Exp Psychol (Hove). 2023. PMID: 36121341 Free PMC article. - Using machine learning analysis to interpret the relationship between music emotion and lyric features.
Xu L, Sun Z, Wen X, Huang Z, Chao CJ, Xu L. Xu L, et al. PeerJ Comput Sci. 2021 Nov 15;7:e785. doi: 10.7717/peerj-cs.785. eCollection 2021. PeerJ Comput Sci. 2021. PMID: 34901433 Free PMC article. - People make mistakes: Obtaining accurate ground truth from continuous annotations of subjective constructs.
Booth BM, Narayanan SS. Booth BM, et al. Behav Res Methods. 2024 Dec;56(8):8784-8800. doi: 10.3758/s13428-024-02503-3. Epub 2024 Sep 30. Behav Res Methods. 2024. PMID: 39349847 Free PMC article. - MERP: A Music Dataset with Emotion Ratings and Raters' Profile Information.
Koh EY, Cheuk KW, Heung KY, Agres KR, Herremans D. Koh EY, et al. Sensors (Basel). 2022 Dec 29;23(1):382. doi: 10.3390/s23010382. Sensors (Basel). 2022. PMID: 36616980 Free PMC article.
References
- Inskip C, Macfarlane A, Rafferty P. Towards the disintermediation of creative music search: analysing queries to determine important facets. International Journal on Digital Libraries. 2012;12(2):137–147. 10.1007/s00799-012-0084-1 - DOI
- Yang YH, Chen HH. Machine recognition of music emotion: A review. ACM Transactions on Intelligent Systems and Technology. 2012;3(3). 10.1145/2168752.2168754 - DOI
- Kim YE, Schmidt EM, Migneco R, Morton BG, Richardson P, Scott J, et al. Music emotion recognition: A state of the art review. In: Proceedings of International Society for Music Information Retrieval Conference; 2010. p. 255–266.
- Laurier C, Lartillot O, Eerola T, Toiviainen P. Exploring relationships between audio features and emotion in music. In: Proceedings of Triennal Conference of European Society for Cognitive Sciences of Music; 2009. p. 260–264.
- Yang YH, Lin YC, Su YF, Chen HH. A regression approach to music emotion recognition. IEEE Transactions on Audio, Speech, and Language Processing. 2008;16(2):448–457. 10.1109/TASL.2007.911513 - DOI
MeSH terms
Grants and funding
AA’s work was supported by COMMIT/ project (commit-nl.nl). MS was supported by Ambizione program of the Swiss National Science Foundation (Grant number PZ00P2_154981).
LinkOut - more resources
Full Text Sources
Other Literature Sources
Miscellaneous