A Likelihood Ratio based Domain Adaptation Method for E2E Models. (arXiv:2201.03655v1 [cs.CL])

End-to-end (E2E) automatic speech recognition models like Recurrent Neural
Networks Transducer (RNN-T) are becoming a popular choice for streaming ASR
applications like voice assistants. While E2E models are very effective at
learning representation of the training data they are trained on, their
accuracy on unseen domains remains a challenging problem. Additionally, these
models require paired audio and text training data, are computationally
expensive and are difficult to adapt towards the fast evolving nature of
conversational speech. In this work, we …

arxiv domain adaptation