--- title: "A Novel Speech Analysis and Correction Tool — Berriche 2024" description: "The authors present ArPA (Arabic Pronunciation Aid), an application for Arabic-speaking children who struggle to pronounce letters of the alphabet." authors: ["Lamia Berriche", "Maha Driss", "Areej Ahmed Almuntashri", "Asma Mufreh Lghabi", "Heba Saleh Almudhi", "Munerah Abdul-Aziz Almansour"] year: 2024 venue: "arXiv:2411.13592" source: "https://arxiv.org/abs/2411.13592" doi: "10.48550/arxiv.2411.13592" arxiv: "2411.13592" licence: "CC BY 4.0 (arXiv)" licence_url: "http://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/berriche-2024-novel-speech-analysis-correction-tool/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/berriche-2024-novel-speech-analysis-correction-tool/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2024](https://md.research.elamur.ai/free/en/papers/2024/page/5/) / A Novel Speech Analysis and Correction Tool for Arabic-Speaking Children # A Novel Speech Analysis and Correction Tool for Arabic-Speaking Children **Authors:** Lamia Berriche, Maha Driss, Areej Ahmed Almuntashri, Asma Mufreh Lghabi, Heba Saleh Almudhi, Munerah Abdul-Aziz Almansour · **Year:** 2024 · **Venue:** arXiv:2411.13592 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://arxiv.org/abs/2411.13592) · [PDF](https://arxiv.org/pdf/2411.13592) · [DOI 10.48550/arxiv.2411.13592](https://doi.org/10.48550/arxiv.2411.13592) · [arXiv 2411.13592](https://arxiv.org/abs/2411.13592) · [OpenAlex](https://openalex.org/W4404649887) **Citations:** 1 citations (OpenAlex, 2026-10-14) ## Summary The authors present ArPA (Arabic Pronunciation Aid), an application for Arabic-speaking children who struggle to pronounce letters of the alphabet. They argue that earlier mispronunciation detectors target adults or non-native learners, or cover only narrow error types such as short vowels. ArPA has two parts. A diagnostic module cleans the recording with Gaussian-filter denoising and silence removal, extracts MFCC and Mel-spectrogram features, renders them as colour images, and classifies each utterance as correct or mispronounced. A therapeutic module is a voice-only game in which an avatar advances a level for each correct letter, and progress reports are available to parents and therapists. Two datasets were used: one recorded at a childcare centre and one of Arabic alphabet pronunciations. Classical baselines (KNN, SVM, Decision Trees) on MFCC features were compared with a fine-tuned ResNet18 on image-converted features. ResNet18 on Mel-spectrogram images performed best, reaching 99.015% accuracy on Dataset 2. The work matters as a child-focused tool that couples automatic diagnosis with motivating practice, although the authors acknowledge that their data is small. ## Key points - Pipeline: denoising with a Gaussian filter, then silence removal, then MFCC or Mel-spectrogram extraction (pre-emphasis, 20–40 ms Hamming-windowed frames, FFT, Mel filter bank, log, plus DCT for MFCC), then min–max colormap conversion to images, then a binary correct/incorrect decision. - Classical baselines on MFCC features: KNN was the strongest on both datasets. On Dataset 2 the three baselines spanned roughly 82%–94% accuracy, and SVM struggled with the small data. - ResNet18 on MFCC images reached 97.53% accuracy on Dataset 1 and 96.24% on Dataset 2. - ResNet18 on Mel-spectrogram images reached 98.77% accuracy on Dataset 1 and 99.015% on Dataset 2. - Training setup: - random 80/20 train/test split; - minibatch size 100, 30 epochs; - learning rate 0.0001 with the Adam optimizer; - results reported as precision, recall, F1, accuracy and per-class confusion matrices. ## Interesting ideas - The uncompressed Mel-spectrogram beat MFCC, its DCT-compressed derivative, and the authors attribute this to the extra time-frequency detail the classifier could exploit. — For Mova (tokens): when building tagger or morphology features, test whether keeping a fuller representation (e.g. all morphological feature values rather than a collapsed tag) improves accuracy before settling on compact encodings. - Recasting a numeric feature matrix as an image, through a simple min–max colormap mapping, lets an off-the-shelf pretrained vision backbone be reused instead of designing a new architecture. — For Mova (tree): gparse experiments could encode pairwise head-dependent score matrices in a form that existing pretrained encoders accept, as a cheap way to borrow capacity. - Cheap classical models (KNN, SVM, Decision Trees) were run first as a baseline floor, so the gain from the deep model is measurable rather than assumed. — For Mova (learn): every new learned component should report a simple baseline alongside it, which acts as a sanity control when judging improvements from silver data or LLM teachers. - Diagnosis drives practice directly: each letter the child fails gets targeted exercises, and per-item progress is logged for a supervising adult. — For Mova (answer): student readers could keep a per-skill mastery log across school-course tests and generate focused drills on the question types they get wrong, with an explainable report. - Evaluation goes beyond overall accuracy to per-class precision, recall and confusion matrices, which confirms that both the "correct" and "mispronounced" classes are handled well. — For Mova (learn): report per-label confusion for dependency relations or semantic roles so that strong majority classes cannot hide failures on rare ones. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* Fields: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/) Topics: [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @misc{berriche2024novel, title = {{A Novel Speech Analysis and Correction Tool for Arabic-Speaking Children}}, author = {Berriche, Lamia and Driss, Maha and Almuntashri, Areej Ahmed and Lghabi, Asma Mufreh and Almudhi, Heba Saleh and Almansour, Munerah Abdul-Aziz}, year = {2024}, doi = {10.48550/arxiv.2411.13592}, eprint = {2411.13592}, archivePrefix = {arXiv}, url = {https://doi.org/10.48550/arxiv.2411.13592} } ``` - [← previous A New Benchmark for Evaluating Automatic Speech Recognition in the Arabic Call Domain](https://md.research.elamur.ai/free/en/papers/obaidah-2024-new-benchmark-evaluating-automatic-speech/) - [next → Aalamaram: A Large-Scale Linguistically Annotated Treebank for the Tamil Language](https://md.research.elamur.ai/free/en/papers/abirami-2024-aalamaram-large-scale-linguistically-annotated/) - [↑ back to papers of 2024](https://md.research.elamur.ai/free/en/papers/2024/page/5/) ## References 1 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. 1. Ahmed, A., Bader, M., Shahin, I., Nassif, A.B., Werghi, N., Basel, M.: Arabic mispronunciation recognition system using lstm network. Information 14(7), 413 Authors Suppressed Due to Excessive Length (2023) 2. Akhtar, S., Hussain, F., Raja, F.R., Ehatisham-ul haq, M., Baloch, N.K., Ishmanov, F., Zikria, Y.B.: Improving mispronunciation detection of arabic words for non-native learners using deep convolutional neural network features. Electronics 9(6), 963 (2020) 3. Algabri, M., Mathkour, H., Alsulaiman, M., Bencherif, M.A.: Mispronunciation detection and diagnosis with articulatory-level feedback generation for non-native arabic speech. Mathematics 10(15), 2727 (2022) 4. Asif, A., Mukhtar, H., Alqadheeb, F., Ahmad, H.F., Alhumam, A.: An approach for pronunciation classification of classical arabic phonemes using deep learning. Applied Sciences 12(1), 238 (2021) 5. Cowan, R.: Language disorders, special needs and mathematics learning. Encyclopedia of mathematics education pp. 447–448 (2020) 6. Das, N., Chakraborty, S., Chaki, J., Padhy, N., Dey, N.: Fundamentals, present and future perspectives of speech enhancement. International Journal of Speech Technology 24, 883–901 (2021) 7. Lloyd-Esenkaya, V., Russell, A.J., Clair, M.C.S.: What are the peer interaction strengths and difficulties in children with developmental language disorder? a systematic review. International Journal of Environmental Research and Public Health 17(9), 3140 (2020) 8. Lounis, M., Dendani, B., Bahi, H.: Anomaly detection with a variational autoencoder for arabic mispronunciation detection. International Journal of Speech Technology pp. 1–12 (2024) 9. Lounis, M., Dendani, B., Bahi, H.: Mispronunciation detection and diagnosis using deep neural networks: a systematic review. Multimedia Tools and Applications pp. 1–35 (2024) 10. Nazir, F., Majeed, M.N., Ghazanfar, M.A., Maqsood, M.: Mispronunciation detection using deep convolutional neural network features and transfer learning-based model for arabic phonemes. IEEE Access 7, 52589–52608 (2019) 11. Smith, N., Gales, M.: Speech recognition using svms. Advances in neural information processing systems 14 (2001) 12. Sun, L., Fu, S., Wang, F.: Decision tree svm model with fisher feature selection for speech emotion recognition. EURASIP Journal on Audio, Speech, and Music Processing 2019(1), 1–14 (2019) 13. Ziafat, N., Ahmad, H.F., Fatima, I., Zia, M., Alhumam, A., Rajpoot, K.: Correct pronunciation detection of the arabic alphabet using deep learning. Applied Sciences 11(6) (2021). https://doi.org/10.3390/app11062508, https://www.mdpi. com/2076-3417/11/6/2508 [↗](https://doi.org/10.3390/app11062508)