Log In Sign Up

Neural Inverse Text Normalization

by   Monica Sunkara, et al.

While there have been several contributions exploring state of the art techniques for text normalization, the problem of inverse text normalization (ITN) remains relatively unexplored. The best known approaches leverage finite state transducer (FST) based models which rely on manually curated rules and are hence not scalable. We propose an efficient and robust neural solution for ITN leveraging transformer based seq2seq models and FST-based text normalization techniques for data preparation. We show that this can be easily extended to other languages without the need for a linguistic expert to manually curate them. We then present a hybrid framework for integrating Neural ITN with an FST to overcome common recoverable errors in production environments. Our empirical evaluations show that the proposed solution minimizes incorrect perturbations (insertions, deletions and substitutions) to ASR output and maintains high quality even on out of domain data. A transformer based model infused with pretraining consistently achieves a lower WER across several datasets and is able to outperform baselines on English, Spanish, German and Italian datasets.


page 1

page 2

page 3

page 4


NeMo Inverse Text Normalization: From Development To Production

Inverse text normalization (ITN) converts spoken-domain automatic speech...

Language Agnostic Data-Driven Inverse Text Normalization

With the emergence of automatic speech recognition (ASR) models, convert...

A Unified Transformer-based Framework for Duplex Text Normalization

Text normalization (TN) and inverse text normalization (ITN) are essenti...

Text normalization for endangered languages: the case of Ligurian

Text normalization is a crucial technology for low-resource languages wh...

indic-punct: An automatic punctuation restoration and inverse text normalization framework for Indic languages

Automatic Speech Recognition (ASR) generates text which is most of the t...

Scalable Multilingual Frontend for TTS

This paper describes progress towards making a Neural Text-to-Speech (TT...

Streaming, fast and accurate on-device Inverse Text Normalization for Automatic Speech Recognition

Automatic Speech Recognition (ASR) systems typically yield output in lex...