OpenBEATs: A Fully Open-Source General-Purpose Audio Encoder

TL;DR

OpenBEATs introduces an open-source, multi-domain audio pre-training framework using masked token prediction, achieving state-of-the-art results across diverse audio understanding tasks and datasets, thereby advancing general-purpose audio representation learning.

Contribution

It extends BEATs with multi-domain pre-training and open-source code, enabling broader application and reproducibility in general audio understanding.

Findings

State-of-the-art performance on bioacoustics and environmental sound datasets.

Effective multi-domain pre-training improves general audio representations.

Models outperform larger models at a fraction of the parameters.

Abstract

Masked token prediction has emerged as a powerful pre-training objective across language, vision, and speech, offering the potential to unify these diverse modalities through a single pre-training task. However, its application for general audio understanding remains underexplored, with BEATs being the only notable example. BEATs has seen limited modifications due to the absence of open-source pre-training code. Furthermore, BEATs was trained only on AudioSet, restricting its broader downstream applicability. To address these gaps, we present OpenBEATs, an open-source framework that extends BEATs via multi-domain audio pre-training. We conduct comprehensive evaluations across six types of tasks, twenty five datasets, and three audio domains, including audio reasoning tasks such as audio question answering, entailment, and captioning. OpenBEATs achieves state-of-the-art performance on six bioacoustics datasets, two environmental sound datasets and five reasoning datasets, performing better than models exceeding a billion parameters at one-fourth their parameter size. These results demonstrate the effectiveness of multi-domain datasets and masked token prediction task to learn general-purpose audio representations. To promote further research and reproducibility, we release all pre-training and evaluation code, pretrained and fine-tuned checkpoints, and training logs at https://shikhar-s.github.io/OpenBEATs