Common Contracts
1 similar Agreement contracts
AGREEMENT AMONG HUMAN AND AUTOMATED ESTIMATES OF SIMILARITY IN A GLOBAL MUSIC SAMPLEAgreement • May 24th, 2022
While music information retrieval (MIR) has made substantial progress in automatic analysis of audio similarity for Western music, it remains unclear whether these algorithms can be mean- ingfully applied to cross-cultural analyses of more diverse mu- sics. Here we collect perceptual ratings from 62 Japanese partici- pants using a global sample of 30 traditional songs, and compare these ratings against both pre-existing expert annotations and au- dio similarity algorithms. We find that different methods of per- ceptual ratings all produced similar, moderate levels of inter-rater agreement comparable to previous studies, but that agreement be- tween human and automated methods is always low regardless of the specific methods used to calculate musical similarity. Our findings suggest that the MIR methods tested are unable to mea- sure cross-cultural music similarity in perceptually meaningful ways.
