“Game-powered machine learning” could make searching for music online easier

When it comes to online music, we really are spoilt for choice. So spoilt it can make uncovering new music to match our tastes or finding a track when we don’t know the artist or song title, a hit and miss affair. Engineers at the University of California, San Diego (UCSD), have developed a new approach called “game-powered machine learning” that they claim is just as accurate as other methods, but is cheaper and has the potential to let users search every song on the web using a text search. We all know how difficult it can be using a text term to search for multimedia content online. Many Internet radio sites, such as Pandora, pay experts in music theory to categorize songs and make catalogs easier to search, but this is time consuming and expensive. Another method, often employed by online music stores, involves basing recommendations on the purchases of others with similar tastes in music. However, this kind of collaborative filtering only works with music that is already popular, severely limiting things for those after something a bit more off the beaten track. Instead of paying experts, the system developed at UCSD relies on a much cheaper source of labor – unpaid music fans. Enticed by an online Facebook game called Herd It, players are asked to place music into different categories (romantic, jazz, saxophone, happy, etc.) after listening to a snippet - this is the “game-powered” bit.

This human knowledge is then used to train the computer, which analyzes the waveforms of songs in these categories looking for commonalities in acoustic patterns – this is the “machine-learning” part. The system can then use these patterns to automatically categorize the millions of songs on the internet – be they popular or previously unheard of. And because the descriptions of the music are in text form, people can search the database using text. “This is a very promising mechanism to address large-scale music search in the future,” said Gert Lanckriet, a professor of electrical engineering at the UC San Diego Jacobs School of Engineering and leader of the UCSD study. To improve its auto-tagging algorithms, the system is also able to automatically create new Herd It games to collect the data it most needs. If it’s struggling recognizing jazz music patterns, for example, it can request more jazz to study. Lanckriet believes a massive database of cataloged music created by the system could work with mobile phone sensors to enable personal radio stations that select music while taking into account a person’s activity and mood. “What I would like long-term is just one single radio station that starts in the morning and it adapts to you throughout the day. By that I mean the user doesn’t have to tell the system, 'Hey, it’s afternoon now, I prefer to listen to hip hop in the afternoon.' The system knows because it has learned the cell phone user’s preferences.” The UCSD team has published the details of their game-powered machine learning technique in a study published in the April 24 issue of the Proceedings of the National Academy of Sciences.