# Learning Domain Specific Language Models for Automatic Speech Recognition through Machine Translation

arXiv: https://arxiv.org/abs/2110.10261 · HTML: https://mlsanity.com/paper/2110.10261/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 39 references that are in the map.
- First posted on arXiv 21 Sep 2021.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks](https://mlsanity.com/paper/1503.00075/) (2015)
- [Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset](https://mlsanity.com/paper/1909.05358/) (2019)
- [Differentially Private Language Models Benefit from Public Pre-training](https://mlsanity.com/paper/2009.05886/) (2020)
- [Neural Lattice-to-Sequence Models for Uncertain Inputs](https://mlsanity.com/paper/1704.00559/) (2017)
- [Lattice-Based Recurrent Neural Network Encoders for Neural Machine Translation](https://mlsanity.com/paper/1609.07730/) (2016)
- [Encoding Word Confusion Networks with Recurrent Neural Networks for Dialog State Tracking](https://mlsanity.com/paper/1707.05853/) (2017)
- [Modeling ASR Ambiguity for Dialogue State Tracking Using Word Confusion Networks](https://mlsanity.com/paper/2002.00768/) (2020)
- [Language Model Bootstrapping Using Neural Machine Translation For Conversational Speech Recognition](https://mlsanity.com/paper/1912.00958/) (2019)

## Built on by (most cited first, 2 of 2)

- [Digits micro-model for accurate and secure transactions](https://mlsanity.com/paper/2402.01931/) (2024)
- [Automatic Speech Recognition for Greek Medical Dictation](https://mlsanity.com/paper/2509.23550/) (2025)

## Abstract (arXiv)

Automatic Speech Recognition (ASR) systems have been gaining popularity in the recent years for their widespread usage in smart phones and speakers. Building ASR systems for task-specific scenarios is subject to the availability of utterances that adhere to the style of the task as well as the language in question. In our work, we target such a scenario wherein task-specific text data is available in a language that is different from the target language in which an ASR Language Model (LM) is expected. We use Neural Machine Translation (NMT) as an intermediate step to first obtain translations of the task-specific text data. We then train LMs on the 1-best and N-best translations and study ways to improve on such a baseline LM. We develop a procedure to derive word confusion networks from NMT beam search graphs and evaluate LMs trained on these confusion networks. With experiments on the WMT20 chat translation task dataset, we demonstrate that NMT confusion networks can help to reduce the perplexity of both n-gram and recurrent neural network LMs compared to those trained only on N-best translations.