Text Generation with Speech Synthesis for ASR Data Augmentation

Aiming at reducing the reliance on expensive human annotations, data synthesis for Automatic Speech Recognition (ASR) has remained an active area of research. While prior work mainly focuses on synthetic speech generation for ASR data augmentation, its combination with text generation methods is con...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Huang, Zhuangqun, Gil, Keren, Jiang, Ziran, Jain, Shashank, Goss-Grubbs, David, Cheng, Nelson, Abtahi, Farnaz, Le, Duc, Zhang, David, D'Avirro, Antony, Campbell-Taylor, Ethan, Salas, Jessie, Irina-Elena Veliche, Chen, Xi
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 22.05.2023
Subjects
Annotations
Automatic speech recognition
Data augmentation
Neural networks
Online AccessGet full text

Cover

More Information
Summary:Aiming at reducing the reliance on expensive human annotations, data synthesis for Automatic Speech Recognition (ASR) has remained an active area of research. While prior work mainly focuses on synthetic speech generation for ASR data augmentation, its combination with text generation methods is considerably less explored. In this work, we explore text augmentation for ASR using large-scale pre-trained neural networks, and systematically compare those to traditional text augmentation methods. The generated synthetic texts are then converted to synthetic speech using a text-to-speech (TTS) system and added to the ASR training data. In experiments conducted on three datasets, we find that neural models achieve 9%-15% relative WER improvement and outperform traditional methods. We conclude that text augmentation, particularly through modern neural approaches, is a viable tool for improving the accuracy of ASR systems.
ISSN:2331-8422