Evaluation of Modeling Music Similarity Perception Via Feature Subset Selection
In this paper, we describe and discuss the evaluation process and results of a content-based music retrieval system that we have developed. In our system, user models embody the ability of evolving and using different music similarity measures for different users. Specifically, a user-supplied relevance feedback and related neural network-based incremental learning procedures allows our system to determine which subset of a set of objective acoustic features approximates more efficiently the subjective music similarity perception of an individual user. The evaluation results verify our hypothesis of a direct relation between subjective music similarity perception and objective acoustic feature subsets. Moreover, it is shown that, after training, retrieved music pieces exhibit significantly improved perceived similarity to user-targeted music pieces.
KeywordsFeature Subset Relevance Feedback Incremental Learning Music Piece Feature Subset Selection
Unable to display preview. Download preview PDF.
- 2.Kumamoto, T.: Design and evaluation of a music retrieval scheme that adapts to the user’s impressions. In: Ardissono, L., Brna, P., Mitrović, A. (eds.) UM 2005. LNCS (LNAI), vol. 3538, pp. 287–296. Springer, Heidelberg (2005)Google Scholar
- 5.Foote, J.T.: Content-based retrieval of music and audio. Procs. Storage and Retrieval for Image and Video Databases (SPIE) 3229, 138–147 (1997)Google Scholar
- 7.Lampropoulos, A.S., Sotiropoulos, D.N., Tsihrintzis, G.A.: Individualization of music similarity perception via feature subset selection. In: Proceedings of Systems, Man and Cybernetics, 2004 IEEE International Conference, SMC 2004 (1), pp. 552–556 (2004)Google Scholar
- 8.Sotiropoulos, D.N., Tsihrintzis, G.A.: Feature Selection-Based Relevance Feedback In Content-Based Retrieval Systems. In: Proceedings of 5th International Workshop on Image Analysis for Multimedia Interactive Services. WIAMIS (2004)Google Scholar
- 9.Sotiropoulos, D.N., Lampropoulos, A.S., Tsihrintzis, G.A.: Artificial Immune System-Based Music Piece Similarity Measures and Database Organization. In: Proceedings of 5th EURASIP Conference on Speech and Image Processing, Multimedia Communications and Services. ECSIPM (2005)Google Scholar
- 10.Lampropoulos, A.S., Lampropoulou, P.S., Tsihrintzis, G.A.: Musical Genre Classification Enhanced by Source Separation Techniques. In: Proceedings of 6th International Conference on Music Information Retrieval. ISMIR (2005)Google Scholar