External Language Model Integration for Factorized Neural Transducers
share
We propose an adaptation method for factorized neural transducers (FNT) with external language models. We demonstrate that both neural and n-gram external LMs add significantly more value when linearly interpolated with predictor output compared to shallow fusion, thus confirming that FNT forces the predictor to act like regular language models. Further, we propose a method to integrate class-based n-gram language models into FNT framework resulting in accuracy gains similar to a hybrid setup. We show average gains of 18 with lexical adaptation across various scenarios and additive gains of up to 60 n-gram and neural LMs.
READ FULL TEXT