Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You and Your Team.

Learn More →

Text normalization with convolutional neural networks

Text normalization with convolutional neural networks Text normalization is a critical step in the variety of tasks involving speech and language technologies. It is one of the vital components of natural language processing, text-to-speech synthesis and automatic speech recognition. Convolutional neural networks (CNNs) have proven their superior performance to recurrent architectures in various application scenarios, like neural machine translation, however their ability in text normalization was not exploited yet. In this paper we investigate and propose a novel CNNs based text normalization method. Training, inference times, accuracy, precision, recall, and F1-score were evaluated on an open-source dataset. The performance of CNNs is evaluated and compared with a variety of different long short-term memory (LSTM) and Bi-LSTM architectures with the same dataset. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png International Journal of Speech Technology Springer Journals

Text normalization with convolutional neural networks

Loading next page...
 
/lp/springer-journals/text-normalization-with-convolutional-neural-networks-hc3vtlEqu2
Publisher
Springer Journals
Copyright
Copyright © 2018 by Springer Science+Business Media, LLC, part of Springer Nature
Subject
Engineering; Signal,Image and Speech Processing; Social Sciences, general; Artificial Intelligence (incl. Robotics)
ISSN
1381-2416
eISSN
1572-8110
DOI
10.1007/s10772-018-9521-x
Publisher site
See Article on Publisher Site

Abstract

Text normalization is a critical step in the variety of tasks involving speech and language technologies. It is one of the vital components of natural language processing, text-to-speech synthesis and automatic speech recognition. Convolutional neural networks (CNNs) have proven their superior performance to recurrent architectures in various application scenarios, like neural machine translation, however their ability in text normalization was not exploited yet. In this paper we investigate and propose a novel CNNs based text normalization method. Training, inference times, accuracy, precision, recall, and F1-score were evaluated on an open-source dataset. The performance of CNNs is evaluated and compared with a variety of different long short-term memory (LSTM) and Bi-LSTM architectures with the same dataset.

Journal

International Journal of Speech TechnologySpringer Journals

Published: May 30, 2018

References