Scaling few-shot spoken word classification with generative meta-continual learning

ArXi:2605.13075v1 Announce Type: cross Few-shot spoken word classification has largely been developed for applications where a small number of classes is considered, and so the potential of larger-scale few-shot spoken word classification remains untapped. This paper investigates the potential of a spoken word classifier to sequentially a model using the Generative Meta-Continual Learning (GeMCL) algorithm and comparing it to repeatedly trained or finetuned baselines.