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 repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2404.06095")

Code

Syntology Ran 7 of 7 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 7 ran with no contract checked.

By repository: official repository: 7 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

nttcslab/m2d officialmentioned in papermentioned on GitHubpytorch report
nttcslab/eval-audio-repr officialmentioned in paperpytorchNOASSERTION 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

7 samples harvested; 7 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

7ran

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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

available_tasks nttcslab/eval-audio-repr/summarize.py official repository ran licence not identified · pointer only · 44e9469142ae7a17 · report
get_cache_info nttcslab/eval-audio-repr/lineareval.py official repository ran licence not identified · pointer only · ea9e4f4392740932 · report
is_zeroshot_ready nttcslab/eval-audio-repr/zeroshot.py official repository ran licence not identified · pointer only · dc2b7e0afed11044 · report
load_pretrained_weights nttcslab/eval-audio-repr/evar/model_utils.py official repository ran licence not identified · pointer only · 64321fd5ab7f96bc · report
mean_max_pooling nttcslab/eval-audio-repr/evar/model_utils.py official repository ran fingerprinted licence not identified · pointer only · 819b9385b29b2563 · report
normalize_spectrogram nttcslab/eval-audio-repr/evar/ar_base.py official repository ran licence not identified · pointer only · 14c8251e8baf656b · report
show_layers_trainable nttcslab/eval-audio-repr/evar/model_utils.py official repository ran licence not identified · pointer only · 94d3057985c9adeb · report

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