Papers › MT3: Multi-Task Multitrack Music Transcription

MT3: Multi-Task Multitrack Music Transcription

4 Nov 2021ICLR 2022 4arXiv:2111.03017archive 2025-07-28

Josh Gardner, Ian Simon, Ethan Manilow, Curtis Hawthorne, Jesse Engel

Automatic Music Transcription (AMT), inferring musical notes from raw audio, is a challenging task at the core of music understanding. Unlike Automatic Speech Recognition (ASR), which typically focuses on the words of a single speaker, AMT often requires transcribing multiple instruments simultaneously, all while preserving fine-scale pitch and timing information. Further, many AMT datasets are "low-resource", as even expert musicians find music transcription difficult and time-consuming. Thus, prior work has focused on task-specific architectures, tailored to the individual instruments of each task. In this work, motivated by the promising results of sequence-to-sequence transfer learning for low-resource Natural Language Processing (NLP), we demonstrate that a general-purpose Transformer model can perform multi-task AMT, jointly transcribing arbitrary combinations of musical instruments across several transcription datasets. We show this unified training framework achieves high-quality transcription results across a range of datasets, dramatically improving performance for low-resource instruments (such as guitar), while preserving strong performance for abundant instruments (such as piano). Finally, by expanding the scope of AMT, we expose the need for more consistent evaluation metrics and better dataset alignment, and provide a strong baseline for this new direction of multi-task AMT.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 6 code samples harvested from 1 repository linked to this paper: 0 ran · 6 unverified.

By repository: official repository: 6 samples from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

magenta/mt3 officialmentioned in paperjaxSyntology: 6 samples, 0 ran · 6 unverified report
kunato/mt3-pytorch jaxSyntology: not harvested report
mimbres/yourmt3 GPL-3.0Syntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

6 samples harvested: 0 ran · 6 unverified. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

6unverified

Licence: 0 of the 6 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from magenta/mt3. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

magenta/mt3 official repository 6 samples, 0 ran · 6 unverified
Decoder in 210 papers mt3/network.py unverified Apache-2.0 (permissive) · 3bdf7ed695eae626 · report
DecoderLayer in 43 papers mt3/network.py unverified Apache-2.0 (permissive) · a7add228a2b5eb4c · report
Encoder in 278 papers mt3/network.py unverified Apache-2.0 (permissive) · 2247e83f2dee9c11 · report
EncoderLayer in 73 papers mt3/network.py unverified Apache-2.0 (permissive) · 2f90947fb1810fa8 · report
T5Config mt3/network.py unverified Apache-2.0 (permissive) · 04ad8eef95f757d8 · report
Transformer in 173 papers mt3/network.py unverified Apache-2.0 (permissive) · 240f4854b8ffb60f · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for MT3 (graph method: MT3). 6 bricks; individually on a fixture: 0 ran · 6 unverified. The assembly has not been run end-to-end.

  1. Transformer entry · level 0 · unverified · 240f4854b8ffb60f
  2. Decoder model · level 0 · unverified · 3bdf7ed695eae626
  3. Encoder model · level 0 · unverified · 2247e83f2dee9c11
  4. T5Config helper · level 0 · unverified · 04ad8eef95f757d8
  5. DecoderLayer model · level 0 · unverified · a7add228a2b5eb4c
  6. EncoderLayer model · level 0 · unverified · 2f90947fb1810fa8

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2111.03017") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Multi-instrument Music TranscriptionMusic TranscriptionSpeech RecognitionTransfer Learningspeech-recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-instrument Music Transcription URMP MT3 Multi F1 59.0 #2 of 3 Archive leaderboard report
Music Transcription MAESTRO MT3 (single dataset) Onset F1 88.0 #8 of 9 Archive leaderboard report
Music Transcription MAESTRO MT3 (multi dataset) Onset F1 86.0 #9 of 9 Archive leaderboard report
Music Transcription Slakh2100 MT3 note-level F-measure-no-offset (Fno) 0.57 #5 of 6 Archive leaderboard report
Music Transcription URMP MT3 Onset F1 77.0 #2 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections