English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The performance of automatic speech recognition (ASR) systems has advancedsubstantially in recent years, particularly for languages for which a largeamount of transcribed speech is available. Unfortunately, for low-resourcelanguages, such as minority languages, regional languages or dialects, ASRperformance generally remains much lower. In this study, we investigate whetherdata 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). Forall four languages, we examine the use of self-training, where an ASR systemtrained with the available human-transcribed data is used to generatetranscriptions, which are then combined with the original data to train a newASR system. For Gronings, for which there was a pre-existing text-to-speech(TTS) system available, we also examined the use of TTS to generate ASRtraining data from text-only sources. We find that using a self-trainingapproach consistently yields improved performance (a relative WER reduction upto 20.5% compared to using an ASR system trained on 24 minutes of manuallytranscribed speech). The performance gain from TTS augmentation for Groningswas even stronger (up to 25.5% relative reduction in WER compared to a systembased on 24 minutes of manually transcribed speech). In sum, our results showthe benefit of using self-training or (if possible) TTS-generated data as anefficient solution to overcome the limitations of data availability forresource-scarce languages in order to improve ASR performance.

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