Papers › M2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language...

M2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language Representation

4 Jun 2024arXiv:2406.02032archive 2025-07-28

Daisuke Niizumi, Daiki Takeuchi, Yasunori Ohishi, Noboru Harada, Masahiro Yasuda, Shunsuke Tsubaki, Keisuke Imoto

Contrastive language-audio pre-training (CLAP) enables zero-shot (ZS) inference of audio and exhibits promising performance in several classification tasks. However, conventional audio representations are still crucial for many tasks where ZS is not applicable (e.g., regression problems). Here, we explore a new representation, a general-purpose audio-language representation, that performs well in both ZS and transfer learning. To do so, we propose a new method, M2D-CLAP, which combines self-supervised learning Masked Modeling Duo (M2D) and CLAP. M2D learns an effective representation to model audio signals, and CLAP aligns the representation with text embedding. As a result, M2D-CLAP learns a versatile representation that allows for both ZS and transfer learning. Experiments show that M2D-CLAP performs well on linear evaluation, fine-tuning, and ZS classification with a GTZAN state-of-the-art of 75.17%, thus achieving a general-purpose audio-language representation.

PaperPDFCode

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

Code

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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Audio ClassificationLinear evaluationSelf-Supervised LearningTransfer Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Audio Classification AudioSet M2D-CLAP/0.7 Test mAP 0.485 #21 of 51 Archive leaderboard report
Audio Classification ESC-50 M2D-CLAP/0.7 Accuracy (5-fold) 97.4 #8 of 29 Archive leaderboard report
Audio Classification ESC-50 M2D-CLAP/0.7 PRE-TRAINING DATASET AudioSet #8 of 29 Archive leaderboard report
Audio Classification ESC-50 M2D-CLAP/0.7 Top-1 Accuracy 97.4 #8 of 29 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

M2D

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