Virtual assistants make use of automatic speech recognition (ASR) to help users answer entity-centric queries. However, spoken entity recognition is a difficult problem, due to the large number of frequently-changing named entities. In addition, resources available for recognition are constrained when ASR is performed on-device. In this work, we investigate the use of probabilistic grammars as language models within the finite-state transducer (FST) framework. We introduce a deterministic approximation to probabilistic grammars that avoids the explicit expansion of non-terminals at model creation time, integrates directly with the FST framework, and is complementary to n-gram models. We obtain a 10% relative word error rate improvement on long tail entity queries compared to when a similarly-sized n-gram model is used without our method.
@article{arxiv.2206.14885,
title = {Space-Efficient Representation of Entity-centric Query Language Models},
author = {Christophe Van Gysel and Mirko Hannemann and Ernest Pusateri and Youssef Oualil and Ilya Oparin},
journal= {arXiv preprint arXiv:2206.14885},
year = {2022}
}