Space-Efficient Representation of Entity-centric Query Language Models

TL;DR

This paper presents a space-efficient method for representing entity-centric query language models using probabilistic grammars within the FST framework, improving recognition accuracy for virtual assistants on resource-constrained devices.

Contribution

It introduces a deterministic approximation to probabilistic grammars that reduces resource usage and integrates with FSTs, enhancing on-device spoken entity recognition.

Findings

10% relative word error rate improvement on long tail entity queries

Efficient space representation of entity-centric language models

Complementary to n-gram models in ASR systems

Abstract

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.