Inverse text normalization (ITN) is used to convert the spoken form output of an automatic speech recognition (ASR) system to a written form. Traditional handcrafted ITN rules can be complex to transcribe and maintain. Meanwhile neural modeling approaches require quality large-scale spoken-written pair examples in the same or similar domain as the ASR system (in-domain data), to train. Both these approaches require costly and complex annotations. In this paper, we present a data augmentation technique that effectively generates rich spoken-written numeric pairs from out-of-domain textual data with minimal human annotation. We empirically demonstrate that ITN model trained using our data augmentation technique consistently outperform ITN model trained using only in-domain data across all numeric surfaces like cardinal, currency, and fraction, by an overall accuracy of 14.44%.
@article{arxiv.2207.09674,
title = {Improving Data Driven Inverse Text Normalization using Data Augmentation},
author = {Laxmi Pandey and Debjyoti Paul and Pooja Chitkara and Yutong Pang and Xuedong Zhang and Kjell Schubert and Mark Chou and Shu Liu and Yatharth Saraf},
journal= {arXiv preprint arXiv:2207.09674},
year = {2022}
}