JSIR dataset drops: 267 jazz recordings with beat, chord and structure annotations
umpedronosapato · x · 2026-10-14
- Researchers Sihun Lee and Dasaem Jeong released JSIR (Jazz Standards dataset for Information Retrieval), an audio-aligned, multi-task dataset of jazz standard recordings.
- It covers 267 recordings (25.6 hours) with beat/downbeat, chord, and structure annotations; each standard includes 4–9 different recording versions for cross-version comparison.
- Repertoire spans Great American Songbook classics to hard bop, from small combos to big band arrangements, selected for adherence to canonical chord changes.
- Annotations were made by the author, a jazz musician; GitHub repo, browser demo, annotation tool, and arXiv preprint are all available.
More from Research
- XPENG's AUGUstus VLA model hits SOTA on NAVSIM and deploys on real vehicles at 12Hz — XPENG-AI · 2026-10-14
- Alibaba study finds most fancy contrastive tricks barely help multimodal embeddings; combos gain 6% — alibaba-multimodal-industrial-ai · 2026-10-14
- Lightricks' APEX pairs hierarchical latents with async denoising for extreme 64-128x diffusion compression — Lightricks · 2026-10-14
- EMHO: Self-Evolving Agent Harness Boosts Frozen Embodied Models via Experience Traces — Hyun Jung Lee · 2026-10-14
- WorldCast: A Distributed Multiplayer World Model That Runs Counter-Strike 2 in Real Time — CUHKSZ · 2026-10-14
- MixLID: A Token-Level Language ID Model Covering 111 Language-Script Combinations — Seongtae Hong · 2026-10-14