Transformer-based Models of Text Normalization for Speech Applications

02/01/2022
by   Jae Hun Ro, et al.
3

Text normalization, or the process of transforming text into a consistent, canonical form, is crucial for speech applications such as text-to-speech synthesis (TTS). In TTS, the system must decide whether to verbalize "1995" as "nineteen ninety five" in "born in 1995" or as "one thousand nine hundred ninety five" in "page 1995". We present an experimental comparison of various Transformer-based sequence-to-sequence (seq2seq) models of text normalization for speech and evaluate them on a variety of datasets of written text aligned to its normalized spoken form. These models include variants of the 2-stage RNN-based tagging/seq2seq architecture introduced by Zhang et al. (2019), where we replace the RNN with a Transformer in one or more stages, as well as vanilla Transformers that output string representations of edit sequences. Of our approaches, using Transformers for sentence context encoding within the 2-stage model proved most effective, with the fine-tuned BERT encoder yielding the best performance.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/31/2016

RNN Approaches to Text Normalization: A Challenge

This paper presents a challenge to the community: given a large corpus o...
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
12/17/2017

DeepNorm-A Deep Learning Approach to Text Normalization

This paper presents an simple yet sophisticated approach to the challeng...
research
08/05/2021

Finetuning Pretrained Transformers into Variational Autoencoders

Text variational autoencoders (VAEs) are notorious for posterior collaps...
research
09/07/2022

AILAB-Udine@SMM4H 22: Limits of Transformers and BERT Ensembles

This paper describes the models developed by the AILAB-Udine team for th...
research
10/06/2021

Sequence-to-Sequence Lexical Normalization with Multilingual Transformers

Current benchmark tasks for natural language processing contain text tha...
research
06/25/2020

Normalizing Text using Language Modelling based on Phonetics and String Similarity

Social media networks and chatting platforms often use an informal versi...

Please sign up or login with your details

Forgot password? Click here to reset