[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [AUDITORY] Measuring perceptual similarity



We ran a series of experiments on music similarity a few years ago, using triadic comparisons. See the linked paper for a description of the method and analysis of the results. The resulting data were quite useful for training algorithms on music similarity.

http://ismir2006.ismir.net/PAPERS/ISMIR06148_Paper.pdf

-Martin


> On Mar 11, 2018, at 7:24 PM, Pat Savage <patsavagenz@xxxxxxxxx> wrote:
> 
> Dear Auditory list (apologies for cross-posting),
> 
> After years of doing feature-based analyses of musical similarity, I finally have the opportunity to run perceptual experiments to obtain data on perceptual similarity with which to compare feature-based analyses against.
> 
> Since this is a new area for me, I’d like to make sure that I don’t reinvent the wheel or miss good existing experimental paradigms. Can anyone point me towards good resources for best practices in running perceptual similarity experiments?
> 
> Cheers,
> ---
> Dr. Patrick Savage
> Project Associate Professor
> Faculty of Environment and Information Studies
> Keio University SFC (Shonan Fujisawa Campus)
> http://PatrickESavage.com
>