# Efficient Dynamic WFST Decoding for Personalized Language Models

arXiv: https://arxiv.org/abs/1910.10670 · HTML: https://mlsanity.com/paper/1910.10670/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Oct 2019.

## Built on by (most cited first, 1 of 1)

- [A Comparison of Methods for OOV-word Recognition on a New Public Dataset](https://mlsanity.com/paper/2107.08091/) (2021)

## Abstract (arXiv)

We propose a two-layer cache mechanism to speed up dynamic WFST decoding with personalized language models. The first layer is a public cache that stores most of the static part of the graph. This is shared globally among all users. A second layer is a private cache that caches the graph that represents the personalized language model, which is only shared by the utterances from a particular user. We also propose two simple yet effective pre-initialization methods, one based on breadth-first search, and another based on a data-driven exploration of decoder states using previous utterances. Experiments with a calling speech recognition task using a personalized contact list demonstrate that the proposed public cache reduces decoding time by factor of three compared to decoding without pre-initialization. Using the private cache provides additional efficiency gains, reducing the decoding time by a factor of five.