# MuScriptor: An Open Model for Multi-Instrument Music Transcription

arXiv: https://arxiv.org/abs/2607.08168 · HTML: https://mlsanity.com/paper/2607.08168/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 32 references that are in the map.
- First posted on arXiv 9 Jul 2026.

## Builds on (most cited first, 15 of 15)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [Simple and Controllable Music Generation](https://mlsanity.com/paper/2306.05284/) (2023)
- [Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset](https://mlsanity.com/paper/1810.12247/) (2018)
- [MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training](https://mlsanity.com/paper/2306.00107/) (2023)
- [Onsets and Frames: Dual-Objective Piano Transcription](https://mlsanity.com/paper/1710.11153/) (2017)
- [MT3: Multi-Task Multitrack Music Transcription](https://mlsanity.com/paper/2111.03017/) (2021)
- [Sequence-to-Sequence Piano Transcription with Transformers](https://mlsanity.com/paper/2107.09142/) (2021)
- [A Foundation Model for Music Informatics](https://mlsanity.com/paper/2311.03318/) (2023)
- [Unaligned Supervision For Automatic Music Transcription in The Wild](https://mlsanity.com/paper/2204.13668/) (2022)
- [YourMT3+: Multi-instrument Music Transcription with Enhanced Transformer Architectures and Cross-dataset Stem Augmentation](https://mlsanity.com/paper/2407.04822/) (2024)
- [Deep Unsupervised Drum Transcription](https://mlsanity.com/paper/1906.03697/) (2019)
- [Towards Realistic Synthetic Data for Automatic Drum Transcription](https://mlsanity.com/paper/2601.09520/) (2026)
- [Advancing Multi-Instrument Music Transcription: Results from the 2025 AMT Challenge](https://mlsanity.com/paper/2603.27528/) (2026)

## Built on by (most cited first, 2 of 2)

- [CPR: Combining global composing, local performing and full-sequence refining in piano rendering with continuous autoregressive modelling](https://mlsanity.com/paper/2609.18216/) (2026)
- [JazzSAMBA: A Synchronous and Asynchronous Multi-take Band Audio Dataset of Jazz Standards for Live Music Models](https://mlsanity.com/paper/2609.34931/) (2026)

## Abstract (arXiv)

Existing methods for automatic music transcription are often limited to single-instrument recordings or fail on complex, real music mixes. Although previous work utilizes synthetic training data, the resulting models generalize poorly, leading to largely unusable transcription output in realistic, multi-instrument settings. In this work, we analyze the effectiveness of synthetic data for pre-training while combining it with fine-tuning on real music audio and post-training using reinforcement learning. We further introduce conditioning on instrument presence to customize transcriptions. Finally, we release MuScriptor, an open-weight multi-instrument music transcription model that works on real-world music recordings from across a diverse range of musical genres.