dc.contributor.author | Ozaki, Y | |
dc.contributor.author | McBride, J | |
dc.contributor.author | Benetos, E | |
dc.contributor.author | Pfordresher, PQ | |
dc.contributor.author | Six, J | |
dc.contributor.author | T. Tierney, A | |
dc.contributor.author | Proutskova, P | |
dc.contributor.author | Sakai, E | |
dc.contributor.author | Kondo, H | |
dc.contributor.author | Fukatsu, H | |
dc.contributor.author | Fujii, S | |
dc.contributor.author | Savage, PE | |
dc.contributor.author | 22nd International Society for Music Information Retrieval Conference (ISMIR) | |
dc.date.accessioned | 2021-08-12T13:16:30Z | |
dc.date.available | 2021-07-09 | |
dc.date.available | 2021-08-12T13:16:30Z | |
dc.date.issued | 2021-11-09 | |
dc.identifier.uri | https://qmro.qmul.ac.uk/xmlui/handle/123456789/73595 | |
dc.description.abstract | Cross-cultural musical analysis requires standardized symbolic representation of sounds such as score notation. However, transcription into notation is usually conducted manually by ear, which is time-consuming and subjective. Our aim is to evaluate the reliability of existing methods for transcribing songs from diverse societies. We had 3 experts independently transcribe a sample of 32 excerpts of traditional monophonic songs from around the world (half a cappella, half with instrumental accompaniment). 16 songs also had pre-existing transcriptions created by 3 different experts. We compared these human transcriptions against one another and against 10 automatic music transcription algorithms. We found that human transcriptions can be sufficiently reliable (~90% agreement, κ ~.7), but current automated methods are not (<60% agreement, κ <.4). No automated method clearly outperformed others, in contrast to our predictions. These results suggest that improving automated methods for cross-cultural music transcription is critical for diversifying MIR. | en_US |
dc.publisher | International Society for Music Information Retrieval | en_US |
dc.title | Agreement among human and annotated transcriptions of global songs | en_US |
dc.type | Conference Proceeding | en_US |
pubs.notes | Not known | en_US |
pubs.publication-status | Accepted | en_US |
pubs.publisher-url | https://ismir2021.ismir.net/ | en_US |
dcterms.dateAccepted | 2021-07-09 | |
rioxxterms.funder | Default funder | en_US |
rioxxterms.identifier.project | Default project | en_US |