# YourMT3+: Multi-instrument Music Transcription with Enhanced Transformer Architectures and Cross-dataset Stem Augmentation

arXiv: https://arxiv.org/abs/2407.04822 · HTML: https://mlsanity.com/paper/2407.04822/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 51 references that are in the map.
- First posted on arXiv 5 Jul 2024.

## Builds on (most cited first, 30 of 30)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning](https://mlsanity.com/paper/1702.03118/) (2017)
- [Adafactor: Adaptive Learning Rates with Sublinear Memory Cost](https://mlsanity.com/paper/1804.04235/) (2018)
- [Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset](https://mlsanity.com/paper/1810.12247/) (2018)
- [UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretraining](https://mlsanity.com/paper/2304.09151/) (2023)
- [CREPE: A Convolutional Representation for Pitch Estimation](https://mlsanity.com/paper/1802.06182/) (2018)
- [Onsets and Frames: Dual-Objective Piano Transcription](https://mlsanity.com/paper/1710.11153/) (2017)
- [Cutting Music Source Separation Some Slakh: A Dataset to Study the Impact of Training Data Quality and Quantity](https://mlsanity.com/paper/1909.08494/) (2019)
- [XLM-E: Cross-lingual Language Model Pre-training via ELECTRA](https://mlsanity.com/paper/2106.16138/) (2021)
- [MT3: Multi-Task Multitrack Music Transcription](https://mlsanity.com/paper/2111.03017/) (2021)
- [Creating A Multi-track Classical Musical Performance Dataset for Multimodal Music Analysis: Challenges, Insights, and Applications](https://mlsanity.com/paper/1612.08727/) (2016)
- [Learning Features of Music from Scratch](https://mlsanity.com/paper/1611.09827/) (2016)
- [CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts](https://mlsanity.com/paper/2405.05949/) (2024)
- [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)
- [ReconVAT: A Semi-Supervised Automatic Music Transcription Framework for Low-Resource Real-World Data](https://mlsanity.com/paper/2107.04954/) (2021)
- [Improving Perceptual Quality of Drum Transcription with the Expanded Groove MIDI Dataset](https://mlsanity.com/paper/2004.00188/) (2020)
- [A Data-Driven Analysis of Robust Automatic Piano Transcription](https://mlsanity.com/paper/2402.01424/) (2024)
- [High Resolution Guitar Transcription via Domain Adaptation](https://mlsanity.com/paper/2402.15258/) (2024)
- [Multitrack Music Transcription with a Time-Frequency Perceiver](https://mlsanity.com/paper/2306.10785/) (2023)
- [nanoT5: A PyTorch Framework for Pre-training and Fine-tuning T5-style Models with Limited Resources](https://mlsanity.com/paper/2309.02373/) (2023)
- [A Streamlined Encoder/Decoder Architecture for Melody Extraction](https://mlsanity.com/paper/1810.12947/) (2018)
- [Deep Audio-Visual Singing Voice Transcription based on Self-Supervised Learning Models](https://mlsanity.com/paper/2304.12082/) (2023)

## Built on by (most cited first, 13 of 13)

- [Aria-MIDI: A Dataset of Piano MIDI Files for Symbolic Music Modeling](https://mlsanity.com/paper/2504.15071/) (2025)
- [Unified Cross-modal Translation of Score Images, Symbolic Music, and Performance Audio](https://mlsanity.com/paper/2505.12863/) (2025)
- [Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering](https://mlsanity.com/paper/2607.20253/) (2026)
- [MuScriptor: An Open Model for Multi-Instrument Music Transcription](https://mlsanity.com/paper/2607.08168/) (2026)
- [Towards Realistic Synthetic Data for Automatic Drum Transcription](https://mlsanity.com/paper/2601.09520/) (2026)
- [Music Transcription with (Almost) No Supervision](https://mlsanity.com/paper/2605.24193/) (2026)
- [Anysynth:Zero-Shot Instrument Cloning via In-Context Learning and Asymmetric Hierarchical Guidance](https://mlsanity.com/paper/2607.11143/) (2026)
- [RUMAA: Repeat-Aware Unified Music Audio Analysis for Score-Performance Alignment, Transcription, and Mistake Detection](https://mlsanity.com/paper/2507.12175/) (2025)
- [Joint Transcription of Acoustic Guitar Strumming Directions and Chords](https://mlsanity.com/paper/2508.07973/) (2025)
- [Decomposer: Learning to Decompile Symbolic Music to Programs](https://mlsanity.com/paper/2607.01849/) (2026)
- [MulTTiPop: A Multitrack Transcription Dataset for Pop Music](https://mlsanity.com/paper/2607.08756/) (2026)
- [Playability-Aware Audio-to-Tablature Guitar Transcription via Diffusion Models](https://mlsanity.com/paper/2608.30854/) (2026)
- [Synthesis and editing of multi-instrument audio mixtures using scalar-quantised latents with MIDI Span conditioning](https://mlsanity.com/paper/2609.25546/) (2026)

## Abstract (arXiv)

Multi-instrument music transcription aims to convert polyphonic music recordings into musical scores assigned to each instrument. This task is challenging for modeling as it requires simultaneously identifying multiple instruments and transcribing their pitch and precise timing, and the lack of fully annotated data adds to the training difficulties. This paper introduces YourMT3+, a suite of models for enhanced multi-instrument music transcription based on the recent language token decoding approach of MT3. We enhance its encoder by adopting a hierarchical attention transformer in the time-frequency domain and integrating a mixture of experts. To address data limitations, we introduce a new multi-channel decoding method for training with incomplete annotations and propose intra- and cross-stem augmentation for dataset mixing. Our experiments demonstrate direct vocal transcription capabilities, eliminating the need for voice separation pre-processors. Benchmarks across ten public datasets show our models' competitiveness with, or superiority to, existing transcription models. Further testing on pop music recordings highlights the limitations of current models. Fully reproducible code and datasets are available with demos at urlhttps://github.com/mimbres/YourMT3.