Related papers: Learning Domain Specific Language Models for Automatic Speech Recognition through Machine Translation

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

URL: http://arxiv.org/abs/2110.10261v1
Date: Tue, 21 Sep 2021 10:29:20 GMT
Title: Learning Domain Specific Language Models for Automatic Speech Recognition through Machine Translation
Authors: Saurav Jha
Abstract summary: We use Neural Machine Translation as an intermediate step to first obtain translations of task-specific text data. We develop a procedure to derive word confusion networks from NMT beam search graphs. We demonstrate that NMT confusion networks can help to reduce the perplexity of both n-gram and recurrent neural network LMs.
Score: 0.0
License: http://creativecommons.org/licenses/by/4.0/
Abstract: 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.