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.

该研究论文侧重于开发和评估使用 XLS-R 300m 模型的自动语音识别 (ASR) 技术。该研究旨在提高 ASR 在将口语转化为书面文本方面的性能，尤其是印度尼西亚语、爪哇语和日惹语。该论文讨论了测试程序、使用的数据集以及训练和评估 ASR 系统中采用的方法。结果显示，XLS-R 300m 模型在 Word Error Rate (WER) 方面取得了有竞争力的度量结果，但在日惹语和日惹语上性能略有一些妥协。5-gram KenLM 语言模型的整合显著降低了 WER 并提高了 ASR 的准确性。该研究通过解决语言多样性问题，提高了 ASR 技术的发展，并为不同语言的性能优化提供了见解。

XLS-R 深度学习模型在资源有限语言：印尼语、爪哇语和巽他语中的多语言 ASR 上应用

XLS-R Deep Learning Model for Multilingual ASR on Low- Resource  Languages: Indonesian, Javanese, and Sundanese

This paper proposes two innovative methodologies to construct customized
Common Voice datasets for low-resource languages like Hindi. The first
methodology leverages Bark, a transformer-based text-to-audio model developed
by Suno, and incorporates Meta's enCodec and a pre-trained HuBert model to
enhance Bark's performance. The second methodology employs Retrieval-Based
Voice Conversion (RVC) and uses the Ozen toolkit for data preparation. Both
methodologies contribute to the advancement of ASR technology and offer
valuable insights into addressing the challenges of constructing customized
Common Voice datasets for under-resourced languages. Furthermore, they provide
a pathway to achieving high-quality, personalized voice generation for a range
of applications.

本文提出了两种创新方法，用于为印地语等低资源语言构建定制的 Common Voice 数据集。第一种方法利用 Suno 开发的基于 Transformer 的文本到音频模型 Bark，结合 Meta 的 enCodec 和预训练的 HuBert 模型来增强 Bark 的性能。第二种方法采用检索式语音转换（RVC），并使用 Ozen 工具包进行数据准备。这两种方法为 ASR 技术的发展做出了贡献，并提供了有价值的见解，以解决构建低资源语言定制 Common Voice 数据集的挑战。此外，它们为实现高质量个性化语音生成提供了途径，适用于各种应用场景。