Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning
This work addresses the need for better audio representations for downstream classification tasks, offering an incremental improvement over existing self-supervised methods.
The paper tackles the problem of improving self-supervised audio representation learning by proposing MATPAC, a method that combines masked latent prediction with unsupervised classification, resulting in state-of-the-art performance on audio classification datasets like OpenMIC, GTZAN, ESC-50, and US8K, and outperforming supervised methods on Magna-tag-a-tune.
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.