XLS-R Deep Learning Model for Multilingual ASR on Low- Resource Languages: Indonesian, Javanese, and Sundanese
This addresses speech recognition for low-resource languages in Indonesia, but is incremental as it applies an existing model to new data.
The researchers tackled automatic speech recognition for Indonesian, Javanese, and Sundanese languages using the XLS-R 300m model, achieving competitive word error rates with a 5-gram KenLM language model significantly reducing errors.
This research paper focuses on the development and evaluation of Automatic Speech Recognition (ASR) technology using the XLS-R 300m model. The study aims to improve ASR performance in converting spoken language into written text, specifically for Indonesian, Javanese, and Sundanese languages. The paper discusses the testing procedures, datasets used, and methodology employed in training and evaluating the ASR systems. The results show that the XLS-R 300m model achieves competitive Word Error Rate (WER) measurements, with a slight compromise in performance for Javanese and Sundanese languages. The integration of a 5-gram KenLM language model significantly reduces WER and enhances ASR accuracy. The research contributes to the advancement of ASR technology by addressing linguistic diversity and improving performance across various languages. The findings provide insights into optimizing ASR accuracy and applicability for diverse linguistic contexts.