Detecting Unintended Memorization in Language-Model-Fused ASR. (arXiv:2204.09606v2 [cs.CL] UPDATED)

End-to-end (E2E) models are often being accompanied by language models (LMs)
via shallow fusion for boosting their overall quality as well as recognition of
rare words. At the same time, several prior works show that LMs are susceptible
to unintentionally memorizing rare or unique sequences in the training data. In
this work, we design a framework for detecting memorization of random textual
sequences (which we call canaries) in the LM training data when one has only
black-box (query) access to …

asr language