Subject: Re: [AUDITORY] Measuring perceptual similarity From: Martin McKinney <martin.mckinney@xxxxxxxx> Date: Mon, 12 Mar 2018 08:53:26 -0500 List-Archive:<http://lists.mcgill.ca/scripts/wa.exe?LIST=AUDITORY>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@xxxxxxxx> wrote: >=20 > Dear Auditory list (apologies for cross-posting), >=20 > 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. >=20 > Since this is a new area for me, I=E2=80=99d like to make sure that I = don=E2=80=99t reinvent the wheel or miss good existing experimental = paradigms. Can anyone point me towards good resources for best practices = in running perceptual similarity experiments? >=20 > Cheers, > --- > Dr. Patrick Savage > Project Associate Professor > Faculty of Environment and Information Studies > Keio University SFC (Shonan Fujisawa Campus) > http://PatrickESavage.com >=20