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

• URL: http://arxiv.org/abs/2606.19747v1
• Date: Thu, 18 Jun 2026 03:22:04 GMT
• Title: A Comparative Study of Pretrained Transformer Models for Quranic ASR: Speech Representations, Label Formats, and Dataset Composition
• Abstract summary: Quran Automatic Speech Recognition (ASR) aims to convert Quranic recitation into text, enabling applications such as aided memorisation tools and Quranic search engines.<n>Existing ASR models often exhibit high Word Error Rates (WER) on user-recited verses and lack full coverage of the Quranic corpus.<n>This paper presents a systematic empirical study of domain-specific fine-tuning of pretrained Transformer-based models for Quranic ASR.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 Rates (WER) on user-recited verses and lack full coverage of the Quranic corpus. This paper presents a systematic empirical study of domain-specific fine-tuning of pretrained Transformer-based models for Quranic ASR, using advanced speech feature extraction methods: Wav2Vec2.0, HuBERT, and XLS-R. These models apply self-supervised learning by masking portions of input audio and using Transformer architectures to learn context-aware speech features. The pretrained models are fine-tuned on a filtered Quranic dataset exceeding 870 hours of professional and user recitations. Through comprehensive ablation studies across feature extractors, output label formats, training strategies, and clip durations, we identify the key factors that affect transcription accuracy in this domain. Our best-performing configuration achieves a WER of 0.08 on the EveryAyah subset and 0.11 on the combined EveryAyah+Tarteel setting, representing roughly a five-percentage-point gain over the Citrinet baseline (WER = 0.163) while reducing combined-model training time from 140 hours to 40 hours. Arabic text without diacritics yields the best fine-tuning results, and Wav2Vec2-XLSR-53 provides the strongest overall representation. Future work includes improving dataset quality and developing phoneme-aware models to extract deeper speech feature representations for Tajweed-sensitive applications.

Related papers

• Scaling Open Discrete Audio Foundation Models with Interleaved Semantic, Acoustic, and Text Tokens [62.56027815951259]
  Current audio language models are predominantly text-first, either extending pre-trained text LLM backbones or relying on semantic-only audio tokens.<n>This paper presents a systematic empirical study of native audio foundation models that apply next-token prediction to audio at scale.
  arXiv  Detail & Related papers  (2026-02-18T18:32:46Z)
• Automatic Pronunciation Error Detection and Correction of the Holy Quran's Learners Using Deep Learning [0.0]
  We build a 98% automated pipeline to produce high-quality Quranic datasets.<n>We use our custom Quran Phonetic Script to encode Tajweed rules.<n>We release all code, data, and models as open-source.
  arXiv  Detail & Related papers  (2025-08-27T15:28:46Z)
• A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Data [46.73430446242378]
  We propose a self-refining framework that enhances ASR performance with only unlabeled datasets.<n>We demonstrate the effectiveness of the framework on Taiwanese Mandarin speech.
  arXiv  Detail & Related papers  (2025-06-10T17:30:32Z)
• QARI-OCR: High-Fidelity Arabic Text Recognition through Multimodal Large Language Model Adaptation [0.8944616102795021]
  We present Qari-OCR, a vision-language models progressively optimized for Arabic.<n>Qari-OCR establishes a new open-source state-of-the-art with a Word Error Rate (WER) of 0.160, Character Error Rate (CER) of 0.061, and BLEU score of 0.737 on diacritically-rich texts.
  arXiv  Detail & Related papers  (2025-06-02T22:21:06Z)
• Multi-Sentence Grounding for Long-term Instructional Video [63.27905419718045]
  We aim to establish an automatic, scalable pipeline for denoising a large-scale instructional dataset. We construct a high-quality video-text dataset with multiple descriptive steps supervision, named HowToStep.
  arXiv  Detail & Related papers  (2023-12-21T17:28:09Z)
• StyleSpeech: Self-supervised Style Enhancing with VQ-VAE-based Pre-training for Expressive Audiobook Speech Synthesis [63.019962126807116]
  The expressive quality of synthesized speech for audiobooks is limited by generalized model architecture and unbalanced style distribution. We propose a self-supervised style enhancing method with VQ-VAE-based pre-training for expressive audiobook speech synthesis.
  arXiv  Detail & Related papers  (2023-12-19T14:13:26Z)
• Code-Switching Text Generation and Injection in Mandarin-English ASR [57.57570417273262]
  We investigate text generation and injection for improving the performance of an industry commonly-used streaming model, Transformer-Transducer (T-T) We first propose a strategy to generate code-switching text data and then investigate injecting generated text into T-T model explicitly by Text-To-Speech (TTS) conversion or implicitly by tying speech and text latent spaces. Experimental results on the T-T model trained with a dataset containing 1,800 hours of real Mandarin-English code-switched speech show that our approaches to inject generated code-switching text significantly boost the performance of T-T models.
  arXiv  Detail & Related papers  (2023-03-20T09:13:27Z)
• Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representations [51.89856133895233]
  Speech restoration (SR) is a task of converting degraded speech signals into high-quality ones. In this study, we propose a robust SR model called Miipher, and apply Miipher to a new SR application. To make our SR model robust against various degradation, we use (i) a speech representation extracted from w2v-BERT for the input feature, and (ii) a text representation extracted from transcripts via PnG-BERT as a linguistic conditioning feature.
  arXiv  Detail & Related papers  (2023-03-03T01:57:16Z)
• Fully Automated End-to-End Fake Audio Detection [57.78459588263812]
  This paper proposes a fully automated end-toend fake audio detection method. We first use wav2vec pre-trained model to obtain a high-level representation of the speech. For the network structure, we use a modified version of the differentiable architecture search (DARTS) named light-DARTS.
  arXiv  Detail & Related papers  (2022-08-20T06:46:55Z)
• Text-To-Speech Data Augmentation for Low Resource Speech Recognition [0.0]
  This research proposes a new data augmentation method to improve ASR models for agglutinative and low-resource languages. Experiments were conducted using the corpus of the Quechua language, which is an agglutinative and low-resource language. An 8.73% improvement in the word-error-rate (WER) of the ASR model is obtained using a combination of synthetic text and synthetic speech.
  arXiv  Detail & Related papers  (2022-04-01T08:53:44Z)
• On the Impact of Word Error Rate on Acoustic-Linguistic Speech Emotion Recognition: An Update for the Deep Learning Era [0.0]
  We create transcripts from the original speech by applying three modern ASR systems. For extraction and learning of acoustic speech features, we utilise openSMILE, openXBoW, DeepSpectrum, and auDeep. We achieve state-of-the-art unweighted average recall values of $73.6,%$ and $73.8,%$ on the speaker-independent development and test partitions of IEMOCAP.
  arXiv  Detail & Related papers  (2021-04-20T17:10:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.