Implementation of relevance feedback for content-based music retrieval based on user prefences

The main task of conventional music retrieval systems is to retrieve a music data, which matches the request of a user. The importance of such systems is expected to increase due to the rapid spread of digital music data formats such as MP3. However, conventional systems can only be used to search a particular song from a database. In this research, we investigate the performance of a conventional music retrieval method to retrieve songs based on the user’s musical preferences. Furthermore, we propose the application of relevance feedback techniques to improve the music retrieval performance. Through evaluation experiments, we prove the effectiveness of our method.