# A Data-Driven Analysis of Robust Automatic Piano Transcription

arXiv: https://arxiv.org/abs/2402.01424 · HTML: https://mlsanity.com/paper/2402.01424/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 21 references that are in the map.
- First posted on arXiv 2 Feb 2024.

## Builds on (most cited first, 12 of 12)

- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset](https://mlsanity.com/paper/1810.12247/) (2018)
- [Onsets and Frames: Dual-Objective Piano Transcription](https://mlsanity.com/paper/1710.11153/) (2017)
- [Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification](https://mlsanity.com/paper/1608.04363/) (2016)
- [MT3: Multi-Task Multitrack Music Transcription](https://mlsanity.com/paper/2111.03017/) (2021)
- [High-resolution Piano Transcription with Pedals by Regressing Onset and Offset Times](https://mlsanity.com/paper/2010.01815/) (2020)
- [Learning Features of Music from Scratch](https://mlsanity.com/paper/1611.09827/) (2016)
- [Sequence-to-Sequence Piano Transcription with Transformers](https://mlsanity.com/paper/2107.09142/) (2021)
- [Unaligned Supervision For Automatic Music Transcription in The Wild](https://mlsanity.com/paper/2204.13668/) (2022)
- [Automatic Piano Transcription with Hierarchical Frequency-Time Transformer](https://mlsanity.com/paper/2307.04305/) (2023)
- [Multitrack Music Transcription with a Time-Frequency Perceiver](https://mlsanity.com/paper/2306.10785/) (2023)
- [Invariances and Data Augmentation for Supervised Music Transcription](https://mlsanity.com/paper/1711.04845/) (2017)

## Built on by (most cited first, 15 of 15)

- [YourMT3+: Multi-instrument Music Transcription with Enhanced Transformer Architectures and Cross-dataset Stem Augmentation](https://mlsanity.com/paper/2407.04822/) (2024)
- [Aria-MIDI: A Dataset of Piano MIDI Files for Symbolic Music Modeling](https://mlsanity.com/paper/2504.15071/) (2025)
- [The GigaMIDI Dataset with Features for Expressive Music Performance Detection](https://mlsanity.com/paper/2502.17726/) (2025)
- [GOAT: A Large Dataset of Paired Guitar Audio Recordings and Tablatures](https://mlsanity.com/paper/2509.22655/) (2025)
- [PianoVAM: A Multimodal Piano Performance Dataset](https://mlsanity.com/paper/2509.08800/) (2025)
- [Quantifying the Corpus Bias Problem in Automatic Music Transcription Systems](https://mlsanity.com/paper/2408.04737/) (2024)
- [Towards Robust Transcription: Exploring Noise Injection Strategies for Training Data Augmentation](https://mlsanity.com/paper/2410.14122/) (2024)
- [Sound and Music Biases in Deep Music Transcription Models: A Systematic Analysis](https://mlsanity.com/paper/2512.14602/) (2025)
- [Pay Attention to the Keys: Visual Piano Transcription Using Transformers](https://mlsanity.com/paper/2411.09037/) (2024)
- [PianoCoRe: Combined and Refined Piano MIDI Dataset](https://mlsanity.com/paper/2605.06627/) (2026)
- [Music Transcription with (Almost) No Supervision](https://mlsanity.com/paper/2605.24193/) (2026)
- [Joint Estimation of Piano Dynamics and Metrical Structure with a Multi-task Multi-Scale Network](https://mlsanity.com/paper/2510.18190/) (2025)
- [Velocity Prediction in Automatic Guitar Transcription](https://mlsanity.com/paper/2606.24912/) (2026)
- [Learning to Predict Performance-induced Emotion Differences in Classical Piano Music](https://mlsanity.com/paper/2607.28876/) (2026)
- [Audio-to-Score Transcription using Pre-trained Features, Data Augmentation, and the New SheetSage-A2S Dataset](https://mlsanity.com/paper/2608.06165/) (2026)

## Abstract (arXiv)

Algorithms for automatic piano transcription have improved dramatically in recent years due to new datasets and modeling techniques. Recent developments have focused primarily on adapting new neural network architectures, such as the Transformer and Perceiver, in order to yield more accurate systems. In this work, we study transcription systems from the perspective of their training data. By measuring their performance on out-of-distribution annotated piano data, we show how these models can severely overfit to acoustic properties of the training data. We create a new set of audio for the MAESTRO dataset, captured automatically in a professional studio recording environment via Yamaha Disklavier playback. Using various data augmentation techniques when training with the original and re-performed versions of the MAESTRO dataset, we achieve state-of-the-art note-onset accuracy of 88.4 F1-score on the MAPS dataset, without seeing any of its training data. We subsequently analyze these data augmentation techniques in a series of ablation studies to better understand their influence on the resulting models.