DuET: Note-Frame Dual Encoding for Piano Performance-to-Score Transcription
Summary
DuET is a dual-encoder transformer that jointly performs MIDI-to-score transcription and beat tracking to improve timing and duration accuracy in expressive piano performance transcription, achieving large MUSTER error reductions on the Gangqinpu dataset.
View Cached Full Text
Cached at: 10/19/26, 03:26 AM
Paper page - DuET: Note-Frame Dual Encoding for Piano Performance-to-Score Transcription
Source: https://huggingface.co/papers/2610.21467
Abstract
DuET is a dual-encoder transformer that jointly performs MIDI-to-score transcription and beat tracking to improve timing and duration accuracy in piano performance transcription.
Transcribing expressive piano performances into scores requires interpreting individual note timings within an underlying metrical structure. However, score attributes are associated with notes, whereas beats may occur without coincident note onsets. We introduce DuET, aDual-Encoder Transformerthat jointly learns note-level performance MIDI-to-score (PM2S) transcription and frame-level beat anddownbeat tracking. Bidirectionalcross-attentionconnects note and frame encoders, while anautoregressive decoderalternates between their representations to predict structured score attributes. We further introduceTimeRoPEand Time-Pitch Rotary Positional Encoding (TPRoPE) to establish a shared performance-time reference and explicitly encode relative temporal and pitch relationships. Evaluations on ASAP, a classical piano dataset, and our curated Gangqinpu dataset, which spans multiple genres with a focus on popular piano music, demonstrate improvements in score timing and notated duration. Compared with the strongest baseline on each dataset, DuET reduces MUSTER mean error from 6.56% to 3.64% on Gangqinpu and from 11.30% to 11.22% on ASAP. Ablations support the benefits of frame-level context, time-based positional encoding, and decoder-history masking. Code, weights, and demos are available at https://github.com/wei-zeng98/DuET.
View arXiv pageView PDFProject pageGitHub13Add to collection
Get this paper in your agent:
hf papers read 2610\.21467
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper1
#### Wayne42/DuET Other• 0.1B• Updated1 day ago • 79 • 2
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2610.21467 in a dataset README.md to link it from this page.
Spaces citing this paper1
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
Multi-Task Multi-Frame Visual Piano Transcription
This paper introduces V2N, the first complete visual piano transcription system that jointly predicts onset, offset, keyhold, and velocity from video, achieving state-of-the-art results on PianoVAM and R3 benchmarks.
PianoKontext: Expressive Performance Rendering from Deadpan Context
PianoKontext generates variable-length expressive piano performances from deadpan MIDI scores by aligning audio and MIDI in latent space using Dynamic Time Warping and flow matching with DiT blocks.
Show HN: I trained a 125M model to autocomplete piano on-device
A developer trained a 125M-parameter transformer model to autocomplete piano performances in real-time on-device using MIDI data and DPO post-training, and released the RollTab app for iOS.
SheetSage2: Coherent Lead-Sheet Transcription with Synthetic Supervision
SheetSage2 is a unified music transcription framework combining synthetic MIDI supervision, task-specific structured decoding, and autoregressive distillation, outperforming prior systems on 12 of 15 benchmark-metric pairs with publicly available model weights and code.
MuScriptor: An Open Model for Multi-Instrument Music Transcription
MuScriptor is an open-source model for multi-instrument music transcription, capable of transcribing recordings into MIDI notes for each instrument without prior knowledge of the instruments present.