Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentation

Abstract

The performance of automatic speech recognition (ASR) systems has advanced substantially in recent years, particularly for languages for which a large amount of transcribed speech is available. Unfortunately, for low-resource languages, such as minority languages, regional languages or dialects, ASR performance generally remains much lower. In this study, we investigate whether data augmentation techniques could help improve low-resource ASR performance, focusing on four typologically diverse minority languages or language variants (West Germanic: Gronings, West-Frisian; Malayo-Polynesian: Besemah, Nasal). For all four languages, we examine the use of selftraining, where an ASR system trained with the available human-transcribed data is used to generate transcriptions, which are then combined with the original data to train a new ASR system. For Gronings, for which there was a preexisting text-to-speech (TTS) system available, we also examined the use of TTS to generate ASR training data from text-only sources. We find that using a self-training approach consistently yields improved performance (a relative WER reduction up to 20.5% compared to using an ASR system trained on 24 minutes of manually transcribed speech). The performance gain from TTS augmentation for Gronings was even stronger (up to 25.5% relative reduction in WER compared to a system based on 24 minutes of manually transcribed speech). In sum, our results show the benefit of using selftraining or (if possible) TTS-generated data as an efficient solution to overcome the limitations of data availability for resource-scarce languages in order to improve ASR performance.

Target Speaker Extraction Using Attention-Enhanced Temporal Convolutional Network

“…This matrix is referred to as the mask. The estimated mask aims to closely resemble the ideal ratio mask (IRM) [13], which is defined in Equation (3).…”

“…It is not only hampered by acoustic interference by background noise such as traffic, crowd noise, but also speaker variability like accents, dialects, microphone quality and so on. Bartelds et al reveal issues such as the diminishing returns of data augmentation in data-rich environments and the oversight of sociolinguistic factors, which are critical in diverse linguistic contexts [3]. Furthermore, Li et al discuss the challenges faced by ASR systems in handling continuous speech sequences and streaming speech, highlighting the need for more sophisticated models to tackle these issues [4].…”