A Large-Scale Evaluation of Acoustic and Subjective Music-Similarity Measures

By Adam Berenzweig, Beth T. Logan, D. Ellis, Brian Whitman. Computer Music Journal, 2004

403 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/47b5c56651922a97d9ccd65127ff8c1f918c4317

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

Feature learning and deep architectures: new directions for music informatics (2013, background): “The predominant approach to compute how similar two music signals sound is to model their Mel-Frequency Cepstral Coefficients (MFCCs) with a Gaussian Mixture Model (GMM) and compute some distance measure between them, e.g. KL-divergence, Earth mover’s distance, etc. (Berenzweig et al. 2004).”
Semantic Annotation and Retrieval of Music and Sound Effects (2008, methodology): “The semantic multinomial representation is also useful for related audio information tasks such as “retrieval-by-semantic-similarity” [34], [35].”
Song-Level Features and Support Vector Machines for Music Classification (2005, methodology): “The support vector machine is a supervised classification system that finds the maximum margin hyperplane separating two classes of data.”
FMA: A Dataset for Music Analysis (2016, neutral): “…103 2005 yes Unique [41] 3,115 3,115 2010 yes 1517-Artists [40] 3,180 1,517 2008 yes LMD [42] 3,227 - 2007 no EBallroom [23] 4,180 - 2016 no USPOP [1] 8,752 400 2003 no CAL10k [44] 10,271 4,597 2010 no MagnaTagATune [20] 25,863 3 230 2009 yes 4 Codaich [28] 26,420 1,941 2006 no FMA 106,574 16,341…”
A Survey of Audio-Based Music Classification and Annotation (2011, background): “ilarity [112], [113], [118], some applications require different forms of similarities being used.”
Improving Timbre Similarity : How high’s the sky ? (2004, methodology): “Once again, the number of kmean or GMM centres is a discussed parameter which has received a vast number of answers : 3 ([2]), 8 ([7]), 16 ([4], [7], [22]), 32([7], [18]), 64([7]).”
Music recommendation by unified hypergraph: combining social media information and music content (2010, methodology): “To compactly represent the music content, in this paper we derive features from Mel-frequency cepstral coefficients (MFCCs) [5].”