DECAR: Deep Clustering for learning general-purpose Audio Representations
This work addresses the need for versatile audio representations across various domains, but it is incremental as it builds on existing self-supervised learning methods from computer vision.
The paper tackles the problem of learning general-purpose audio representations by introducing DECAR, a self-supervised pre-training approach based on clustering, which achieves competitive performance on 9 downstream classification tasks including speech, music, and acoustic scenes.
We introduce DECAR, a self-supervised pre-training approach for learning general-purpose audio representations. Our system is based on clustering: it utilizes an offline clustering step to provide target labels that act as pseudo-labels for solving a prediction task. We develop on top of recent advances in self-supervised learning for computer vision and design a lightweight, easy-to-use self-supervised pre-training scheme. We pre-train DECAR embeddings on a balanced subset of the large-scale Audioset dataset and transfer those representations to 9 downstream classification tasks, including speech, music, animal sounds, and acoustic scenes. Furthermore, we conduct ablation studies identifying key design choices and also make all our code and pre-trained models publicly available.