Fast contextual adaptation has shown to be effective in improving Automatic Speech Recognition (ASR) of rare words and when combined with an on-device personalized training, it can yield an even better recognition result. However, the traditional re-scoring approaches based on an external language model is prone to diverge during the personalized training. In this work, we introduce a model-based end-to-end contextual adaptation approach that is decoder-agnostic and amenable to on-device personalization. Our on-device simulation experiments demonstrate that the proposed approach outperforms the traditional re-scoring technique by 12% relative WER and 15.7% entity mention specific F1-score in a continues personalization scenario.
@article{arxiv.2110.02220,
title = {Fast Contextual Adaptation with Neural Associative Memory for On-Device Personalized Speech Recognition},
author = {Tsendsuren Munkhdalai and Khe Chai Sim and Angad Chandorkar and Fan Gao and Mason Chua and Trevor Strohman and Françoise Beaufays},
journal= {arXiv preprint arXiv:2110.02220},
year = {2021}
}