论文信息 - Improving compression based dissimilarity measure for music score analysis

Improving compression based dissimilarity measure for music score analysis

In this paper, we propose a way to improve the compression based dissimilarity measure, CDM. We propose to use a modified value of the file size, where the original CDM uses an unmodified file size. Our application is a music score analysis. We have chosen piano pieces from five different composers. We have selected 75 famous pieces (15 pieces for each composer). We computed the distances among all pieces by using the modified CDM. We use the K-nearest neighbor method when we estimate the composer of each piece of music. The modified CDM shows improved accuracy. The difference is statistically significant.

Ayaka Takamoto | Mitsuo Yoshida | Kyoji Umemura | Mayu Umemura

[1] Kenneth Sörensen,et al. Composer Classification Models for Music-Theory Building , 2016, Computational Music Analysis.

[2] Meinard Müller,et al. Tonal complexity features for style classification of classical music , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[3] Paul M. B. Vitányi,et al. Clustering by compression , 2003, IEEE Transactions on Information Theory.

[4] Kenneth Sörensen,et al. Classification and Generation of Composer-Specific Music Using Global Feature Models and Variable Neighborhood Search , 2015, Computer Music Journal.

[5] David Meredith,et al. Using general-purpose compression algorithms for music analysis , 2016 .

[6] Ronald de Wolf,et al. Algorithmic Clustering of Music Based on String Compression , 2004, Computer Music Journal.

[7] Kjell Lemström,et al. Compression-based Similarity Measures in Symbolic, Polyphonic Music , 2011, ISMIR.

[8] Eamonn J. Keogh,et al. Towards parameter-free data mining , 2004, KDD.

[9] David S. Watson,et al. A Machine Learning Approach to Musical Style Recognition , 1997, ICMC.

[10] Hideo Bannai,et al. Polyphonic Music Classification on Symbolic Data Using Dissimilarity Functions , 2012, ISMIR.