We propose Neural-FST Class Language Model (NFCLM) for end-to-end speech
recognition, a novel method that combines neural network language models
(NNLMs) and finite state transducers (FSTs) in a mathematically consistent
framework. Our method utilizes a background NNLM which models generic
background text together with a collection of domain-specific entities modeled
as individual FSTs. Each output token is generated by a mixture of these
components; the mixture weights are estimated with a separately trained neural
decider. We show that NFCLM significantly outperforms NNLM by 15.8% relative in
terms of Word Error Rate. NFCLM achieves similar performance as traditional
NNLM and FST shallow fusion while being less prone to overbiasing and 12 times
more compact, making it more suitable for on-device usage.

提出了一种新方法 -- 神经 - FST 级语言模型（NFCLM），它将神经网络语言模型（NNLM）和有限状态转换器（FST）结合起来用于端到端语音识别，这种方法通过背景 NNLM 模拟通用背景文本和称为 FST 的一系列特定领域实体 。