Title :
A personalized music filtering system based on melody style classification
Author :
Kuo, Fang-Fei ; Shan, Man-Kwan
Author_Institution :
Dept. of Comput. Sci., Nat. Cheng Chi Univ., Taipei, Taiwan
Abstract :
With the growth of digital music, the personalized music filtering system is helpful for users. Melody style is one of the music features to represent user´s music preference. We present a personalized content-based music filtering system to support music recommendation based on user´s preference of melody style. We propose the multitype melody style classification approach to recommend the music objects. The system learns the user preference by mining the melody patterns from the music access behavior of the user. A two-way melody preference classifier is therefore constructed for each user. Music recommendation is made through this melody preference classifier. Performance evaluation shows that the filtering effect of the proposed approach meets user´s preference.
Keywords :
classification; content-based retrieval; data mining; learning (artificial intelligence); music; user interfaces; content-based filtering system; data mining; digital music; learning; melody style classification; music recommendation; performance evaluation; personalized music filtering system; two-way melody preference classifier; user preference; Collaboration; Computer science; Digital filters; Feature extraction; Information filtering; Information filters; Multiple signal classification; Navigation; Recommender systems; Spatial databases;
Conference_Titel :
Data Mining, 2002. ICDM 2003. Proceedings. 2002 IEEE International Conference on
Print_ISBN :
0-7695-1754-4
DOI :
10.1109/ICDM.2002.1184020