Online Continual Learning of End-to-End Speech Recognition Models. (arXiv:2207.05071v1 [cs.LG])

Continual Learning, also known as Lifelong Learning, aims to continually
learn from new data as it becomes available. While prior research on continual
learning in automatic speech recognition has focused on the adaptation of
models across multiple different speech recognition tasks, in this paper we
propose an experimental setting for \textit{online continual learning} for
automatic speech recognition of a single task. Specifically focusing on the
case where additional training data for the same task becomes available
incrementally over time, we …

arxiv continual learning lg speech speech recognition speech recognition models