Papers › Scoring Time Intervals using Non-Hierarchical Transformer For Automatic Piano Transcription
Scoring Time Intervals using Non-Hierarchical Transformer For Automatic Piano Transcription
Yujia Yan, Zhiyao Duan
The neural semi-Markov Conditional Random Field (semi-CRF) framework has demonstrated promise for event-based piano transcription. In this framework, all events (notes or pedals) are represented as closed time intervals tied to specific event types. The neural semi-CRF approach requires an interval scoring matrix that assigns a score for every candidate interval. However, designing an efficient and expressive architecture for scoring intervals is not trivial. This paper introduces a simple method for scoring intervals using scaled inner product operations that resemble how attention scoring is done in transformers. We show theoretically that, due to the special structure from encoding the non-overlapping intervals, under a mild condition, the inner product operations are expressive enough to represent an ideal scoring matrix that can yield the correct transcription result. We then demonstrate that an encoder-only structured non-hierarchical transformer backbone, operating only on a low-time-resolution feature map, is capable of transcribing piano notes and pedals with high accuracy and time precision. The experiment shows that our approach achieves the new state-of-the-art performance across all subtasks in terms of the F1 measure on the Maestro dataset.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Music Transcription | MAESTRO | Transkun V2 (SemiCRF) | Onset F1 | 98.32 | #1 of 9 | Archive leaderboard | report |
| Music Transcription | MAPS | Transkun V2 (SemiCRF) with Data Augmentation | Onset F1 | 90.38 | #1 of 6 | Archive leaderboard | report |
| Music Transcription | MAPS | Transkun V2 (SemiCRF) | Onset F1 | 86.1 | #5 of 6 | Archive leaderboard | report |
| Music Transcription | SMD Piano | Transkun V2 (SemiCRF) with Data Augmentation | Onset F1 | 98.71 | #1 of 1 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections