Caching Networks: Capitalizing on Common Speech for ASR
Anastasios Alexandridis, Grant P. Strimel, Ariya Rastrow, Pavel Kveton, Jon Webb, Maurizio Omologo, Siegfried Kunzmann, Athanasios Mouchtaris
Abstract
We introduce Caching Networks (CachingNets), a speech recognition network architecture capable of delivering faster, more accurate decoding by leveraging common speech patterns. By explicitly incorporating select sentences unique to each user into the network’s design, we show how to train the model as an extension of the popular sequence transducer architecture through a multitask learning procedure. We further propose and experiment with different phrase caching policies, which are effective for virtual voice-assistant (VA) applications, to complement the architecture. Our results demonstrate that by pivoting between different inference strategies on the fly, CachingNets can deliver significant performance improvements. Specifically, on an industrial-scale, VA ASR task, we observe up to 7.4% relative word error rate (WER) and 11% sentence error rate (SER) improvements with accompanied latency gains.
BibTeX
@inproceedings{icassp2022_cachingnetworksc,
title = {Caching Networks: Capitalizing on Common Speech for ASR},
author = {Anastasios Alexandridis and Grant P. Strimel and Ariya Rastrow and Pavel Kveton and Jon Webb and Maurizio Omologo and Siegfried Kunzmann and Athanasios Mouchtaris},
booktitle = {ICASSP 2022},
year = {2022}
}