Papers › Masked Modeling Duo: Towards a Universal Audio Pre-training Framework

Masked Modeling Duo: Towards a Universal Audio Pre-training Framework

9 Apr 2024arXiv:2404.06095archive 2025-07-28

Daisuke Niizumi, Daiki Takeuchi, Yasunori Ohishi, Noboru Harada, Kunio Kashino

Self-supervised learning (SSL) using masked prediction has made great strides in general-purpose audio representation. This study proposes Masked Modeling Duo (M2D), an improved masked prediction SSL, which learns by predicting representations of masked input signals that serve as training signals. Unlike conventional methods, M2D obtains a training signal by encoding only the masked part, encouraging the two networks in M2D to model the input. While M2D improves general-purpose audio representations, a specialized representation is essential for real-world applications, such as in industrial and medical domains. The often confidential and proprietary data in such domains is typically limited in size and has a different distribution from that in pre-training datasets. Therefore, we propose M2D for X (M2D-X), which extends M2D to enable the pre-training of specialized representations for an application X. M2D-X learns from M2D and an additional task and inputs background noise. We make the additional task configurable to serve diverse applications, while the background noise helps learn on small data and forms a denoising task that makes representation robust. With these design choices, M2D-X should learn a representation specialized to serve various application needs. Our experiments confirmed that the representations for general-purpose audio, specialized for the highly competitive AudioSet and speech domain, and a small-data medical task achieve top-level performance, demonstrating the potential of using our models as a universal audio pre-training framework. Our code is available online for future studies at https://github.com/nttcslab/m2d

PaperPDFCodeCode Syntology ran

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 7 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 7 samples from 1 repository, 7 ran (4 with no instrument failure; 3 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

nttcslab/m2d officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Masked Modeling Duo: Learning Representations by Encouraging Both Networks to Model the Input (arXiv:2210.14648; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
nttcslab/eval-audio-repr officialmentioned in paperpytorchNOASSERTIONSyntology: 7 samples, 7 ran (3 instrument-failed) · 0 unverified 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

7 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
1ran · our draft was wrong
2ran; the contract check could not run
3ran

Licence: 7 of the 7 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 nttcslab/eval-audio-repr. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape. “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.

nttcslab/eval-audio-repr official repository 7 samples, 7 ran (3 instrument-failed) · 0 unverified
available_tasks summarize.py ran · our draft was wrong licence not identified · pointer only · 44e9469142ae7a17 · report fixture: signature df:DataFrame/0/? · returned list · level recorded 2026-09-24
get_cache_info lineareval.py ran licence not identified · pointer only · ea9e4f4392740932 · report fixture: returned tuple · level recorded 2026-09-24
is_zeroshot_ready zeroshot.py ran · violated contract licence not identified · pointer only · dc2b7e0afed11044 · report fixture: signature cfg:MockConfig/0/? · returned bool · level recorded 2026-09-24
load_pretrained_weights in 20 papers evar/model_utils.py ran licence not identified · pointer only · 64321fd5ab7f96bc · report fixture: signature model:callable/0/?, pathname:str/0/str, model_key:str/0/str, strict:bool/0/bool · returned list · level recorded 2026-09-24
mean_max_pooling evar/model_utils.py ran; the contract check could not run (RAISES) fingerprinted licence not identified · pointer only · 819b9385b29b2563 · report fixture: signature frame_embeddings:Tensor/3/float, dim:int/0/int · returned Tensor · level recorded 2026-09-24
normalize_spectrogram evar/ar_base.py ran; the contract check could not run (RAISES) licence not identified · pointer only · 14c8251e8baf656b · report fixture: signature norm_stats:tuple/1/Tensor, spectrograms:Tensor/3/float · returned Tensor · level recorded 2026-09-24
show_layers_trainable evar/model_utils.py ran licence not identified · pointer only · 94d3057985c9adeb · report fixture: signature layer:callable/0/?, show_all_trainable:bool/0/bool, print_str:bool/0/bool · returned str · level recorded 2026-09-24

Tasks

Audio ClassificationDenoisingEnvironment Sound ClassificationLinear evaluationSelf-Supervised LearningSpeaker Identification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Google Speech Commands V2 35 M2D/0.7 ACC 98.4 #1 of 1 Archive leaderboard report
VoxCeleb1 M2D/0.7 Acc 96.3 #1 of 1 Archive leaderboard report
Audio Classification Audio Set M2D-AS/0.7 Mean AP 48.5 #1 of 3 Archive leaderboard report
Audio Classification AudioSet M2D-AS/0.7 Test mAP 0.485 #22 of 51 Archive leaderboard report
Audio Classification AudioSet M2D/0.7 Test mAP 0.479 #27 of 51 Archive leaderboard report
Audio Classification ESC-50 M2D-AS/0.7 Accuracy (5-fold) 97.2 #9 of 29 Archive leaderboard report
Audio Classification ESC-50 M2D-AS/0.7 PRE-TRAINING DATASET AudioSet #9 of 29 Archive leaderboard report
Audio Classification ESC-50 M2D-AS/0.7 Top-1 Accuracy 97.2 #9 of 29 Archive leaderboard report
Audio Classification ESC-50 M2D/0.7 Accuracy (5-fold) 96.0 #14 of 29 Archive leaderboard report
Audio Classification ESC-50 M2D/0.7 Top-1 Accuracy 96.0 #14 of 29 Archive leaderboard report
Audio Classification ICBHI Respiratory Sound Database M2D-X/0.7 (η=0.3) ICBHI Score 63.29 #5 of 25 Archive leaderboard report
Audio Classification ICBHI Respiratory Sound Database M2D/0.7 (e=0.3) ICBHI Score 62.73 #7 of 25 Archive leaderboard report
Speaker Identification VoxCeleb1 MSM-MAE Accuracy 96.6 #1 of 12 Archive leaderboard report
Speaker Identification VoxCeleb1 MSM-MAE Top-1 (%) 96.6 #1 of 12 Archive leaderboard report
Speaker Identification VoxCeleb1 M2D/0.6 Accuracy 96.5 #2 of 12 Archive leaderboard report
Speaker Identification VoxCeleb1 M2D/0.6 Top-1 (%) 96.5 #2 of 12 Archive leaderboard report
Speaker Identification VoxCeleb1 M2D/0.7 Accuracy 96.3 #3 of 12 Archive leaderboard report
Speaker Identification VoxCeleb1 M2D/0.7 Top-1 (%) 96.3 #3 of 12 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

Introduced by this paper: M2D

BYOLM2D

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