Text normalization using memory augmented neural networks

We perform text normalization, i.e. the transformation of words from the written to the spoken form, using a memory augmented neural network. With the addition of dynamic memory access and storage mechanism, we present a neural architecture that will serve as a language-agnostic text normalization s...

Full description

Saved in:
Bibliographic Details
Published in:Speech communication 2019-05, Vol.109, p.15-23
Main Authors: Pramanik, Subhojeet, Hussain, Aman
Format: Article
Language:English
Subjects:
Computer architecture
Deep learning
Differentiable Neural Computer
Neural networks
Performance enhancement
Recurrent neural networks
Semiotics
Text normalization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We perform text normalization, i.e. the transformation of words from the written to the spoken form, using a memory augmented neural network. With the addition of dynamic memory access and storage mechanism, we present a neural architecture that will serve as a language-agnostic text normalization system while avoiding the kind of unacceptable errors made by the LSTM-based recurrent neural networks. By successfully reducing the frequency of such mistakes, we show that this novel architecture is indeed a better alternative. Our proposed system requires significantly lesser amounts of data, training time and compute resources. Additionally, we perform data up-sampling, circumventing the data sparsity problem in some semiotic classes, to show that sufficient examples in any particular class can improve the performance of our text normalization system. Although a few occurrences of these errors still remain in certain semiotic classes, we demonstrate that memory augmented networks with meta-learning capabilities can open many doors to a superior text normalization system.
ISSN:0167-6393
1872-7182
DOI:10.1016/j.specom.2019.02.003