Note-Level Transcription of Choral Music

Choral music is a musical activity with one of the largest participant bases, yet it has drawn little attention from automatic music transcription research. The main reasons we argue are due to the lack of data and technical difficulties arise from diverse acoustic conditions and unique properties of choral singing. To address these challenges, in this paper we propose a Transformer-based framework for note-level transcription of choral music. This framework bypasses the frame-level processing and directly produces a sequence of notes with associated timestamps. We also introduce YouChorale, a novel choral music dataset in a cappella setting curated from the Internet. YouChorale contains 452 real-world recordings in diverse acoustic configurations of choral music from over 100 composers as well as their MIDI scores. Trained on YouChorale, our proposed model achieves state-of-the-art performance in choral music transcription, marking a significant advancement in the field.