Papers › Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning
Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning
Aurian Quelennec, Pierre Chouteau, Geoffroy Peeters, Slim Essid
Recently, self-supervised learning methods based on masked latent prediction have proven to encode input data into powerful representations. However, during training, the learned latent space can be further transformed to extract higher-level information that could be more suited for downstream classification tasks. Therefore, we propose a new method: MAsked latenT Prediction And Classification (MATPAC), which is trained with two pretext tasks solved jointly. As in previous work, the first pretext task is a masked latent prediction task, ensuring a robust input representation in the latent space. The second one is unsupervised classification, which utilises the latent representations of the first pretext task to match probability distributions between a teacher and a student. We validate the MATPAC method by comparing it to other state-of-the-art proposals and conducting ablations studies. MATPAC reaches state-of-the-art self-supervised learning results on reference audio classification datasets such as OpenMIC, GTZAN, ESC-50 and US8K and outperforms comparable supervised methods results for musical auto-tagging on Magna-tag-a-tune.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Audio Classification | ESC-50 | MATPAC (SSL model, linear eval) | Accuracy (5-fold) | 93.5 | #18 of 29 | Archive leaderboard | report |
| Audio Classification | ESC-50 | MATPAC (SSL model, linear eval) | PRE-TRAINING DATASET | AudioSet | #18 of 29 | Archive leaderboard | report |
| Audio Classification | ESC-50 | MATPAC (SSL model, linear eval) | Top-1 Accuracy | 93.5 | #18 of 29 | Archive leaderboard | report |
| Audio Classification | FSD50K | MATPAC (SSL Model) | mAP | 55.2 | #7 of 10 | Archive leaderboard | report |
| Environmental Sound Classification | UrbanSound8K | MATPAC (SSL, linear eval) | Accuracy | 89.4 | #2 of 3 | Archive leaderboard | report |
| Instrument Recognition | NSynth | MATPAC (SSL, linear eval) | Accuracy | 74.6 | #4 of 7 | Archive leaderboard | report |
| Instrument Recognition | OpenMIC-2018 | MATPAC (SSL Model, linear eval) | mean average precision | 0.854 | #2 of 5 | Archive leaderboard | report |
| Music Auto-Tagging | MagnaTagATune | MATPAC (SSL, linear eval) | PR-AUC | 41.1 | #2 of 3 | Archive leaderboard | report |
| Music Auto-Tagging | MagnaTagATune | MATPAC (SSL, linear eval) | ROC AUC | 91.6 | #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.
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