Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems
Abstract
Speech and audio systems operate in inherently non-stationary environments, yet continual learning (CL) research in this domain, especially in the foundation model era, remains fragmented that fail to account for the coupled, geometry-sensitive nature of acoustic representations. Modern speech foundation models operate over highly entangled, continuous representations that jointly encode linguistic, speaker, and paralinguistic factors within a shared latent space. CL is therefore fundamentally about preserving and evolving shared representation structure rather than retaining isolated task knowledge. In this work, we revisit CL for speech from a representation-centered perspective, and introduce a new taxonomy that organizes CL according to how underlying representation geometry evolves under non-stationary acoustic conditions. We further identify key mismatches between current CL assumptions and speech foundation model behavior, and finally outline a set of open challenges and future research directions.
Keywords
Cite
@article{arxiv.2605.24863,
title = {Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems},
author = {Yang Xiao and Siyi Wang and Eun-Jung Holden and Ting Dang},
journal= {arXiv preprint arXiv:2605.24863},
year = {2026}
}
Comments
4 pages, 1 figure, working in process