PulseAugur
实时 16:34:08
English(EN) A Comparative Study of Pretrained Transformer Models for Quranic ASR: Speech Representations, Label Formats, and Dataset Composition

Transformer模型在古兰经自动语音识别方面准确性有所提高

研究人员对用于古兰经自动语音识别(ASR)的预训练Transformer模型进行了比较研究,旨在降低用户诵读经文时的高词错误率(WER)。该研究在870小时的古兰经数据集上微调了Wav2Vec2.0、HuBERT和XLS-R等模型,确定了转录准确性的关键因素。最佳配置在EveryAyah子集上实现了0.08的WER,相比Citrinet基线有了显著改进,同时还缩短了训练时间。 AI

影响 提高了特定ASR任务的准确性和效率,可能有助于古兰经研究和普及。

排序理由 学术论文,详细介绍了AI模型在特定任务上的比较研究。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

Transformer模型在古兰经自动语音识别方面准确性有所提高

报道来源 [1]

  1. arXiv cs.AI TIER_1 English(EN) · Nabil Mosharraf Hossain (Greentech Apps Foundation, United Kingdom), Riasat Islam (Greentech Apps Foundation, United Kingdom, Queen Mary University of London, United Kingdom), Unaizah Obaidellah (University of Malaya, Malaysia) ·

    A Comparative Study of Pretrained Transformer Models for Quranic ASR: Speech Representations, Label Formats, and Dataset Composition

    arXiv:2606.19747v1 Announce Type: new Abstract: Quran Automatic Speech Recognition (ASR) aims to convert Quranic recitation into text, enabling applications such as aided memorisation tools and Quranic search engines. However, existing ASR models often exhibit high Word Error Rat…