AnalysisMusicAugust 7, 2026

New SheetSage-A2S dataset targets audio-to-score for popular music

The paper introduces SheetSage-A2S, a dataset with 61 hours of audio paired with **kern scores, aimed at improving audio-to-score transcription for popular music, an area underexplored compared to classical. It also uses pre-trained features and data augmentation.

1 source

Daily brief

Get tomorrow's AI brief in your inbox

More stories today

Open the live feed