Text Generation with Speech Synthesis for ASR Data Augmentation
This work addresses data scarcity in ASR systems, offering a practical tool for improving accuracy, though it is incremental as it builds on existing text and speech synthesis methods.
The paper tackled the problem of reducing reliance on expensive human annotations for Automatic Speech Recognition (ASR) by exploring text augmentation combined with speech synthesis, achieving 9%-15% relative WER improvement on three datasets.
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.