Automatic Music Transcription and Ethnomusicology: a User Study

Converting an acoustic music signal into music notation using a computer program has been at the forefront of music information research for several decades, as a task referred to as automatic music transcription (AMT). However, current AMT research is still constrained to system development followed by quantitative evaluations; it is still unclear whether the performance of AMT methods is considered sufficient to be used in the everyday practice of music scholars. In this paper, we propose and carry out a user study on evaluating the usefulness of automatic music transcription in the context of ethnomusicology. As part of the study, we recruited 16 participants who were asked to transcribe short musical excerpts either from scratch or using the output of an AMT system as a basis. We collect and analyze quantitative measures such as transcription time and effort, and a range of qualitative feedback from study participants, which includes user needs, criticisms of AMT technologies, and links between perceptual and quantitative evaluations on AMT outputs. The results show no quantitative advantage of using AMT, but important indications regarding appropriate user groups and evaluation measures are provided