GeMCL scales few-shot spoken word classification to 1000 classes with 5 shots each, matching frozen-HuBERT baseline performance while adapting 2000 times faster on less than half the data.
Learning to C ontinually L earn with the B ayesian P rinciple
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Multilingual generative meta-learning for spoken word classification shows small gains over monolingual models, with unique data volume mattering more than the number of languages.
citing papers explorer
-
Scaling few-shot spoken word classification with generative meta-continual learning
GeMCL scales few-shot spoken word classification to 1000 classes with 5 shots each, matching frozen-HuBERT baseline performance while adapting 2000 times faster on less than half the data.
-
Does language matter for spoken word classification? A multilingual generative meta-learning approach
Multilingual generative meta-learning for spoken word classification shows small gains over monolingual models, with unique data volume mattering more than the number of languages.