Mufin Brings Better Music Recommendations to iTunes
When we first reviewed Mufin, a music recommendation service that is entirely based around algorithms that can automatically detect the similarities between different songs, we only gave it a pretty average review. Since then, however, Mufin has greatly improved its service and added Facebook and Myspace applications. The most interesting new product, however, is Mufin's iTunes plugin, which brings Mufin's recommendation engine to your own iTunes collection and allows you to create automatic playlists based solely on the musical similarities between the songs.
In our tests, Mufin often performed better than Apple's Genius feature, but for now, the plugin is only available for Windows.
Editor's note: Looking back over 2008, there were some posts on ReadWriteWeb that did not get the attention we felt they deserved - whether because of timing, competing news stories, etc. So in this end-of-year series, called Redux, we're resurrecting some of those hidden gems. This is one of them, we hope you enjoy (re)reading it!
Fingerprinting
Mufin creates a unique fingerprint for every song in your library when you start the plugin for the first time. You can choose if you want the recommendations to be based on the analysis of 30 second snippets (for fast analysis) or on the whole song (very slow, but highly accurate). Mufin's proprietary algorithms can then create playlists based on the similarities between the songs in your library. In creating these fingerprints, Mufin looks at over 40 characteristics, including tempo, instruments, and rhythm structure.
Apple's algorithms, on the other hand, are hidden in a black box, but seem to be based around the listening and purchasing habits of other users on iTunes.
Mufin's approach means that it will work for any song you may have imported into iTunes, no matter whether it is part of Apple's library or not. Mufin is also agnostic as to what language the songs are in.
Similar to Apple's Genius, the Mufin plugin will also make purchasing recommendations for similar songs that are not yet in your iTunes library and take you right to the iTunes store to listen to the preview or purchase them.
Verdict
Overall, we have come away very impressed with Mufin's recommendations. Judging from what we have seen so far, it may just replace the Genius feature as our preferred way of constructing automatic playlists.
That said, we are still not great fans of Mufin's core web service, which, unlike the plugin, is encumbered by licensing problems and which can only play 30 seconds of most songs (and often can't play the songs at all). The plugin, however, is a clear winner in our eyes.
Share
Comments
Subscribe to comments for this post OR Subscribe to comments for all ReadWriteWeb posts
Maybe the positive recognition Mufin has received points to a rise in content-analysis based recommendations (whether automated like Mufin, manual like Pandora, or a mix) for music and other media. Collaborative filtering methods like Genius seems to use have definite limitations in accuracy and in recommending surprising and less well-known titles.
This is a good idea but by far Pandora has the best algorithm for suggesting music. It usually delivers great songs that you would want to hear.
We've seen visualizer plugins come and go for iTunes, but I didn't know you could create this type of plugin. I've been looking for audio related plugins like equalizers and DSP's. Anyone have any clue where I could find any? A list perhaps?