# Towards Realistic Synthetic Data for Automatic Drum Transcription

arXiv: https://arxiv.org/abs/2601.09520 · HTML: https://mlsanity.com/paper/2601.09520/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 14 Jan 2026.

## Builds on (most cited first, 8 of 8)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [MT3: Multi-Task Multitrack Music Transcription](https://mlsanity.com/paper/2111.03017/) (2021)
- [YourMT3+: Multi-instrument Music Transcription with Enhanced Transformer Architectures and Cross-dataset Stem Augmentation](https://mlsanity.com/paper/2407.04822/) (2024)
- [Towards multi-instrument drum transcription](https://mlsanity.com/paper/1806.06676/) (2018)
- [ADTOF: A large dataset of non-synthetic music for automatic drum transcription](https://mlsanity.com/paper/2111.11737/) (2021)
- [Toward Deep Drum Source Separation](https://mlsanity.com/paper/2312.09663/) (2023)
- [Annotation-free Automatic Music Transcription with Scalable Synthetic Data and Adversarial Domain Confusion](https://mlsanity.com/paper/2312.10402/) (2023)
- [Analyzing and reducing the synthetic-to-real transfer gap in Music Information Retrieval: the task of automatic drum transcription](https://mlsanity.com/paper/2407.19823/) (2024)

## Built on by (most cited first, 1 of 1)

- [MuScriptor: An Open Model for Multi-Instrument Music Transcription](https://mlsanity.com/paper/2607.08168/) (2026)

## Abstract (arXiv)

Deep learning models define the state-of-the-art in Automatic Drum Transcription (ADT), yet their performance is contingent upon large-scale, paired audio-MIDI datasets, which are scarce. Existing workarounds that use synthetic data often introduce a significant domain gap, as they typically rely on low-fidelity SoundFont libraries that lack acoustic diversity. While high-quality one-shot samples offer a better alternative, they are not available in a standardized, large-scale format suitable for training. This paper introduces a new paradigm for ADT that circumvents the need for paired audio-MIDI training data. Our primary contribution is a semi-supervised method to automatically curate a large and diverse corpus of one-shot drum samples from unlabeled audio sources. We then use this corpus to synthesize a high-quality dataset from MIDI files alone, which we use to train a sequence-to-sequence transcription model. We evaluate our model on the ENST and MDB test sets, where it achieves new state-of-the-art results, significantly outperforming both fully supervised methods and previous synthetic-data approaches. The code for reproducing our experiments is publicly available at https://github.com/pier-maker92/ADT_STR