TY - JOUR
T1 - AGREEMENT AMONG HUMAN AND AUTOMATED TRANSCRIPTIONS OF GLOBAL SONGS
AU - Ozaki, Yuto
AU - McBride, John
AU - Benetos, Emmanouil
AU - Pfordresher, Peter Q.
AU - Six, Joren
AU - Tierney, Adam T.
AU - Proutskova, Polina
AU - Sakai, Emi
AU - Kondo, Haruka
AU - Fukatsu, Haruno
AU - Fujii, Shinya
AU - Savage, Patrick E.
N1 - Publisher Copyright:
© Yuto Ozaki, John McBride, Emmanouil Benetos, Peter Q. Pfordresher, Joren Six, Adam T. Tierney, Polina Proutskova, Emi Sakai, Haruka Kondo, Haruno Fukatsu, Shinya Fujii, Patrick E. Savage.
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/85219569651
M3 - Article
AN - SCOPUS:85219569651
SN - 3006-3094
VL - 2021
SP - 500
EP - 508
JO - Proceedings of the International Society for Music Information Retrieval Conference
JF - Proceedings of the International Society for Music Information Retrieval Conference
ER -