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
- Skeptic shares first impressions of ChatGPT Plus
- Hard sci-fi authors largely oppose LLMs, survey finds
- Anthropic tests folderless Claude Code sessions on Desktop and iOS
- Ethan Mollick: Using weaker AI for human-facing content may soon be disrespectful
- Pocket TTS training stack open-sourced