Training Autoregressive Speech Recognition Models with Limited in-domain Supervision. (arXiv:2210.15135v1 [cs.CL])

Advances in self-supervised learning have significantly reduced the amount of
transcribed audio required for training. However, the majority of work in this
area is focused on read speech. We explore limited supervision in the domain of
conversational speech. While we assume the amount of in-domain data is limited,
we augment the model with open source read speech data. The XLS-R model has
been shown to perform well with limited adaptation data and serves as a strong
baseline. We use untranscribed …

arxiv speech speech recognition speech recognition models training