Paper Detail

SheetSage2: Coherent Lead-Sheet Transcription with Synthetic Supervision

Junyan Jiang, Ruibin Yuan, Jiahao Pan, Wei Xue, Yike Guo, Gus Xia, Yann LeCun

huggingface Score 6.0

Published 2026-10-04 · First seen 2026-10-08

General AI

Abstract

Transcribing music into a human-readable score requires a coherent understanding of rhythm, harmony, melody, and form. Two obstacles limit this goal: annotated recordings are scarce, and accurate local predictions can still produce inconsistent musical sequences. We present SheetSage2, a unified music transcription framework that combines synthetic data, task-specific structured decoding, and autoregressive distillation. Automatically annotated MIDI, rendered into audio, provides scalable supervision across music understanding tasks. Task-specific structured decoders integrate complementary musical cues and their temporal dependencies to produce musically coherent scores. Autoregressive distillation further retains transcription accuracy without task-specific dynamic programming at inference. Across eight benchmark collections, a single SheetSage2-AR model exceeds the listed prior systems on 12 of 15 benchmark--metric pairs in our evaluation, substantially improving over SheetSage1 and surpassing task-specific models on several benchmarks. Model weights and inference code are publicly available.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{jiang2026sheetsage2,
  title = {SheetSage2: Coherent Lead-Sheet Transcription with Synthetic Supervision},
  author = {Junyan Jiang and Ruibin Yuan and Jiahao Pan and Wei Xue and Yike Guo and Gus Xia and Yann LeCun},
  year = {2026},
  abstract = {Transcribing music into a human-readable score requires a coherent understanding of rhythm, harmony, melody, and form. Two obstacles limit this goal: annotated recordings are scarce, and accurate local predictions can still produce inconsistent musical sequences. We present SheetSage2, a unified music transcription framework that combines synthetic data, task-specific structured decoding, and autoregressive distillation. Automatically annotated MIDI, rendered into audio, provides scalable superv},
  url = {https://huggingface.co/papers/2610.05336},
  keywords = {huggingface daily},
  eprint = {2610.05336},
  archiveprefix = {arXiv},
}

Metadata

{}