learning style from more than one example?

[ianni67]

trafficstars

I'm trying to understand if it would make sense to learn style from a group of examples (in this case, audio files) instead of just one. In the best case this would produce a sort of "mean style" representing the group of audio excerpts. In your experience, would such an approach work (as long as the examples do somehow share some style in common), or it would produce just garbage?

[DmitryUlyanov]

Hi, I never tried it for audio, should be very easy to implement though. Send me results if you try it.

[msm1089]

@ianni67 Did you ever give learning form multiple examples a go? Sounds interesting...like you could style a piece of audio as a genre, by learning from a bunch of tracks of a specific genre.

@DmitryUlyanov Anything you could point me towards to get started with trying this?