Computer Audition: From Task-Specific Machine Learning to Foundation Models

TL;DR

This paper reviews the shift from traditional task-specific audio analysis methods to the development of general-purpose foundation models in computer audition, emphasizing their advantages and potential to unify multiple audio tasks.

Contribution

It provides an overview of how foundation models are transforming computational audio analysis and highlights key principles enabling multi-task capabilities.

Findings

Foundation models unify multiple audio tasks.

They leverage cross-modal knowledge.

They facilitate human interaction with audio systems.

Abstract

Foundation models (FMs) are increasingly spearheading recent advances on a variety of tasks that fall under the purview of computer audition -- the use of machines to understand sounds. They feature several advantages over traditional pipelines: among others, the ability to consolidate multiple tasks in a single model, the option to leverage knowledge from other modalities, and the readily-available interaction with human users. Naturally, these promises have created substantial excitement in the audio community, and have led to a wave of early attempts to build new, general-purpose foundation models for audio. In the present contribution, we give an overview of computational audio analysis as it transitions from traditional pipelines towards auditory foundation models. Our work highlights the key operating principles that underpin those models, and showcases how they can accommodate multiple tasks that the audio community previously tackled separately.