Personalized Content-Based Music Retrieval by User-Filtering and Query-Refinement

In recent years, music is an important media because it can relax us in our daily life. Therefore, most people listen to music frequently and current music websites offer online listening services. However, because the semantic gap, it is not easy to effectively retrieve the user preferred music especially from a huge amount of music data. For this issue, this paper presents a personalized content-based music retrieval system that integrates techniques of user-filtering and query-refinement to achieve high quality of music retrieval. In terms of user-filtering, the new user interest can be inferred by the user similarities. In terms of query-refinement, the user interest can be guided to the potential search space by iterative feedbacks. The experimental results show the proposed method does improve the retrieval quality significantly.