Leveraging Pre-Trained Autoencoders for Interpretable Prototype Learning of Music Audio
This work addresses interpretability in music audio classification, particularly for genre recognition, but is incremental as it builds on existing prototype learning methods.
The authors tackled the problem of interpretable music audio classification by decoupling autoencoder and prototypical network training, leveraging pre-trained autoencoders for better generalization. They found that prototype-based models preserved most performance from autoencoder embeddings, with sonification aiding classifier interpretability.
We present PECMAE, an interpretable model for music audio classification based on prototype learning. Our model is based on a previous method, APNet, which jointly learns an autoencoder and a prototypical network. Instead, we propose to decouple both training processes. This enables us to leverage existing self-supervised autoencoders pre-trained on much larger data (EnCodecMAE), providing representations with better generalization. APNet allows prototypes' reconstruction to waveforms for interpretability relying on the nearest training data samples. In contrast, we explore using a diffusion decoder that allows reconstruction without such dependency. We evaluate our method on datasets for music instrument classification (Medley-Solos-DB) and genre recognition (GTZAN and a larger in-house dataset), the latter being a more challenging task not addressed with prototypical networks before. We find that the prototype-based models preserve most of the performance achieved with the autoencoder embeddings, while the sonification of prototypes benefits understanding the behavior of the classifier.