Papers › Audio Embeddings as Teachers for Music Classification

Audio Embeddings as Teachers for Music Classification

30 Jun 2023arXiv:2306.17424archive 2025-07-28

Yiwei Ding, Alexander Lerch

Music classification has been one of the most popular tasks in the field of music information retrieval. With the development of deep learning models, the last decade has seen impressive improvements in a wide range of classification tasks. However, the increasing model complexity makes both training and inference computationally expensive. In this paper, we integrate the ideas of transfer learning and feature-based knowledge distillation and systematically investigate using pre-trained audio embeddings as teachers to guide the training of low-complexity student networks. By regularizing the feature space of the student networks with the pre-trained embeddings, the knowledge in the teacher embeddings can be transferred to the students. We use various pre-trained audio embeddings and test the effectiveness of the method on the tasks of musical instrument classification and music auto-tagging. Results show that our method significantly improves the results in comparison to the identical model trained without the teacher's knowledge. This technique can also be combined with classical knowledge distillation approaches to further improve the model's performance.

PaperPDFCode

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

ClassificationInformation RetrievalInstrument RecognitionKnowledge DistillationMusic Auto-TaggingMusic ClassificationMusic Information RetrievalRetrievalTransfer Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instrument Recognition OpenMIC-2018 EAsT-KD + PaSST mean average precision .852 #3 of 5 Archive leaderboard report
Instrument Recognition OpenMIC-2018 EAsT-Final + PaSST mean average precision .847 #4 of 5 Archive leaderboard report
Music Auto-Tagging MagnaTagATune (clean) EAsT-KD + PaSST PR-AUC 46.1 #2 of 3 Archive leaderboard report
Music Auto-Tagging MagnaTagATune (clean) EAsT-KD + PaSST ROC-AUC 91.5 #2 of 3 Archive leaderboard report
Music Auto-Tagging MagnaTagATune (clean) EAsT-Final + PaSST PR-AUC 45.9 #3 of 3 Archive leaderboard report
Music Auto-Tagging MagnaTagATune (clean) EAsT-Final + PaSST ROC-AUC 91.2 #3 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

Knowledge Distillation

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