NeMo Inverse Text Normalization: From Development To Production

04/11/2021
by   Yang Zhang, et al.
0

Inverse text normalization (ITN) converts spoken-domain automatic speech recognition (ASR) output into written-domain text to improve the readability of the ASR output. Many state-of-the-art ITN systems use hand-written weighted finite-state transducer(WFST) grammars since this task has extremely low tolerance to unrecoverable errors. We introduce an open-source Python WFST-based library for ITN which enables a seamless path from development to production. We describe the specification of ITN grammar rules for English, but the library can be adapted for other languages. It can also be used for written-to-spoken text normalization. We evaluate the NeMo ITN library using a modified version of the Google Text normalization dataset.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/26/2022

Four-in-One: A Joint Approach to Inverse Text Normalization, Punctuation, Capitalization, and Disfluency for Automatic Speech Recognition

Features such as punctuation, capitalization, and formatting of entities...
research
03/31/2022

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...
research
08/23/2021

A Unified Transformer-based Framework for Duplex Text Normalization

Text normalization (TN) and inverse text normalization (ITN) are essenti...
research
02/12/2021

Neural Inverse Text Normalization

While there have been several contributions exploring state of the art t...
research
05/31/2018

Text Normalization using Memory Augmented Neural Networks

We propose a memory augmented neural network to perform text normalizati...
research
01/20/2023

Language Agnostic Data-Driven Inverse Text Normalization

With the emergence of automatic speech recognition (ASR) models, convert...
research
09/12/2023

Improving Robustness of Neural Inverse Text Normalization via Data-Augmentation, Semi-Supervised Learning, and Post-Aligning Method

Inverse text normalization (ITN) is crucial for converting spoken-form i...

Please sign up or login with your details

Forgot password? Click here to reset