# Few-Shot Drum Transcription in Polyphonic Music

arXiv: https://arxiv.org/abs/2008.02791 · HTML: https://mlsanity.com/paper/2008.02791/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Aug 2020.

## Built on by (most cited first, 7 of 7)

- [Foundation Models for Music: A Survey](https://mlsanity.com/paper/2408.14340/) (2024)
- [Leveraging Hierarchical Structures for Few-Shot Musical Instrument Recognition](https://mlsanity.com/paper/2107.07029/) (2021)
- [Few-shot bioacoustic event detection at the DCASE 2022 challenge](https://mlsanity.com/paper/2207.07911/) (2022)
- [LC-Protonets: Multi-Label Few-Shot Learning for World Music Audio Tagging](https://mlsanity.com/paper/2409.11264/) (2024)
- [Show Me the Instruments: Musical Instrument Retrieval from Mixture Audio](https://mlsanity.com/paper/2211.07951/) (2022)
- [Towards Human-in-the-Loop Onset Detection: A Transfer Learning Approach for Maracatu](https://mlsanity.com/paper/2507.04858/) (2025)
- [Episode-specific Fine-tuning for Metric-based Few-shot Learners with Optimization-based Training](https://mlsanity.com/paper/2506.17499/) (2025)

## Abstract (arXiv)

Data-driven approaches to automatic drum transcription (ADT) are often limited to a predefined, small vocabulary of percussion instrument classes. Such models cannot recognize out-of-vocabulary classes nor are they able to adapt to finer-grained vocabularies. In this work, we address open vocabulary ADT by introducing few-shot learning to the task. We train a Prototypical Network on a synthetic dataset and evaluate the model on multiple real-world ADT datasets with polyphonic accompaniment. We show that, given just a handful of selected examples at inference time, we can match and in some cases outperform a state-of-the-art supervised ADT approach under a fixed vocabulary setting. At the same time, we show that our model can successfully generalize to finer-grained or extended vocabularies unseen during training, a scenario where supervised approaches cannot operate at all. We provide a detailed analysis of our experimental results, including a breakdown of performance by sound class and by polyphony.