Search Inside the Music: Using Signal Processing, Machine Learning, and 3-D Visualizations to Discover New Music
TS-1548

This presentation discusses Search Inside the Music, a Sun Laboratories research project that is exploring new ways to help people discover new music even as our music collections get very large.

As online music collections grow to many millions of songs, finding a new song we might like is becoming very difficult. The Search Inside the Music system can help you find new music by finding music that sounds like music we already know and like.

SITM, written entirely in the Java programming language, uses digital signal processing and machine learning algorithms to build a music-similarity model that can predict how similar or dissimilar a pair of songs sound. SITM uses this model to recommend music by finding music that sounds similar to music you already know and like.

Not only can you use this music-similarity model to help recommend music but you can also use the model to generate a more engaging, immersive interface to your music. SITM uses the music-similarity model to generate a "music space," a 3-D representation of a music collection, in which songs are positioned according to music similarity. In this music space, classical music may be clustered in one corner, trying to stay as far away from punk music as possible, whereas blues finds a home near, but separate from, jazz and rock. This visualization encourages music exploration. You can audition new songs by clicking on a song in the visualization and find similar-sounding songs by clicking on a song's neighbors. You can generate interesting playlists by creating paths through this music space.

The presentation discusses some of the problems inherent in traditional music recommenders and how a content-based approach to music recommendation can help improve music recommendations. It covers some of the algorithms involved in building a music-similarity model, including the digital-signal-processing algorithms used for extracting music features and the machine-learning algorithms for identifying significant patterns in music. It also discusses some of the algorithms used to generate immersive interactive visualizations of a music space, using the Java 3D API. It concludes with a demonstration of the Search Inside the Music system.

Watch The Session
You need to be a registered Sun Developer Network member to view this multimedia session. If you are a registered SDN member, please click on "Watch Multimedia" button to log-in to view the multimedia session. If you wish to join SDN, please click here.