How to leverage dynamic contextual information in end-to-end speech recognition has remained an active research area. Previous solutions to this problem were either designed for specialized use cases that did not generalize well to open-domain scenarios, did not scale to large biasing lists, or underperformed on rare long-tail words. We address these limitations by proposing a novel solution that combines shallow fusion, trie-based deep biasing, and neural network language model contextualization. These techniques result in significant 19.5% relative Word Error Rate improvement over existing contextual biasing approaches and 5.4%-9.3% improvement compared to a strong hybrid baseline on both open-domain and constrained contextualization tasks, where the targets consist of mostly rare long-tail words. Our final system remains lightweight and modular, allowing for quick modification without model re-training.
@article{arxiv.2104.02194,
title = {Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion},
author = {Duc Le and Mahaveer Jain and Gil Keren and Suyoun Kim and Yangyang Shi and Jay Mahadeokar and Julian Chan and Yuan Shangguan and Christian Fuegen and Ozlem Kalinli and Yatharth Saraf and Michael L. Seltzer},
journal= {arXiv preprint arXiv:2104.02194},
year = {2021}
}