I’m sure you heard of the major minor music game. It was posted on the music-ir list and Paul has blogged about it. You probably also know that Paul recently lost his lead (he had the highest overall score for at least a week I think), and that many other researchers (including Martin and myself) had made it into the top 10 at some point.
The clever game was also mentioned on the Listening Post. It would be nice to see it climb high in Digg’s playable web games section.
Maybe such games could be the solution to automatic segmentation, music classification, maybe also music recommendation, and replace various other content-based techniques we are still working on?
Instead of teaching computers how to understand music we just need to find clever ways to motivate those 8.5 millions playing World of Warcraft to play similar games. I think that might even solve the various scalability issues Jeremy and Paul mentioned recently.
Subscribe to:
Post Comments (Atom)
2 comments:
Hi Elias, thanks for the digg! My vision for this project is not to put us researchers out of business with cheap human labor, but to collect enough human data to better ground our automatic systems. While it is possible to harness the power of people's free time to solve the problems you mention, it seems much more widely applicable and flexible to be able to do it automatically.
Didn't Luis von Ahn say something similar? ;-)
I'm not too serious about challenging content-based MIR. Afterall, that's still what I do, and I have no plans to quit anytime soon. But sometimes I do wonder what the alternatives are...
What if games like yours turn out to be a big success? What if more and more users tag the music they listen to on last.fm? Maybe we would see more and more applications based on those tags? Maybe the demand for tagged data would rise? Maybe at some point the demand would be so high, that content producers might start tagging the contents they create?
At that point it would also be nice if content producers would supply us with their master recordings (-> voice speration, melody extraction, and beat tracking the easy way). It would also be nice to have the lyrics (synchronized), the score, the video, the guitar tabs, and everything else that would be nice to use for MIR research. (Having all that for free would be great, after all music wants to be free.)
Anyway, I hope you'll be giving us some more insights about the MajorMinor game at ISMIR in Vienna! :-)
Post a Comment