COMPARATIVE STUDY ON OPTICAL MUSIC RECOGNITION OF STRING QUARTET SCORES

Dongmin Kim, Brian Liu, Jose J. Valero-Mas, Dasaem Jeong

Submission Type: 2-page Extended Abstract (Non-archival) / 2페이지 Extended Abstract (프로시딩 미수록)

Keywords: Optical music recognition, OMR, Music information retrieval, Staff notation, String quartet

Abstract: Optical music recognition (OMR) transcribes music scores into digital formats. While the field has advanced significantly on monophonic and pianoform scores, multi-part score transcription remains underexplored. This paper addresses this gap with two contributions. First, we propose an OMR variant of the OpenScore String Quartet corpus, the first string quartet dataset variant dedicated to OMR, with scanned image pairings and visual corrections to match source materials. Second, we conduct a systematic comparative study of state-of-the-art OMR methods on multi-part string quartet scores, evaluating decoding formats, model architectures, and segmentation strategies using the OMR-NED metric. Our findings show that staff-wise processing outperforms system-level approaches for string quartet score recognition.

Email Sharing: We authorize sharing author emails with Program Chairs. / 저자 이메일 공유에 동의합니다.

Data Release: We understand and agree to the OpenReview metadata visibility policy. / OpenReview 메타데이터 공개 정책을 이해하고 동의합니다.

Submission Number: 29