Pengembangan Model Prediksi Speech Recognition dengan Algoritma Deep Learning Convolutional Neural Network

Authors

  • Abdul Halim Anshor Teknik Informatika, Universitas Pelita Bangsa
  • Aswan Supriyadi Sunge Teknik Informatika, Universitas Pelita Bangsa

DOI:

https://doi.org/10.33020/saintekom.v16i1.1020

Keywords:

sundanese language, automatic speech recognition, convolutional neural network, mel-frequency cepstral coefficients, language dialect

Abstract

This study examines the development of an automatic speech recognition (ASR) system in Sundanese, which still faces data limitations. Dialect variations and the lack of labeled data are the main challenges in the speech recognition process. The approach used is a Convolutional Neural Network (CNN) with Mel-Frequency Cepstral Coefficients (MFCC) feature extraction. The data used were 100 voice recordings consisting of West Sundanese and South Sundanese dialects. The processing process was carried out through the stages of pre-emphasis, framing, windowing, Fourier transform, Mel filter bank, and Discrete Cosine Transform to obtain voice features. The data was divided into 80% training data and 20% test data. The CNN model was then trained to recognize the voice patterns of each dialect. Based on the test results, the model achieved an accuracy of 70% with a loss value of 0.60. These results indicate that the approach used can be applied to limited data, although its performance can still be improved in further research.

Downloads

Download data is not yet available.

References

Akhiril Anwar Harahap, Novita, R., Ahsyar, T. K., & Zarnelly, Z. (2024). Classification of Beef and Pork with Deep Learning Approach. Jurnal Sistem Cerdas, 7(1), 55–65. https://doi.org/10.37396/jsc.v7i1.393

Aminuddin, M. (2023). English Spoken Digit Recognition using Convolutional Neural Network (CNN). Jurnal EEICT (Electric Electronic Instrumentation Control Telecommunication), 6(2). https://doi.org/10.31602/eeict.v6i2.11877

Azis, N., Herwanto, H., & Ramadhani, F. (2021). Implementasi Speech Recognition Pada Aplikasi E-Prescribing Menggunakan Algoritme Convolutional Neural Network. JURNAL MEDIA INFORMATIKA BUDIDARMA, 5(2), 460. https://doi.org/10.30865/mib.v5i2.2841

International, O. T. (2024). Retracted: A Classroom Emotion Recognition Model Based on a Convolutional Neural Network Speech Emotion Algorithm. Occupational Therapy International, 2024(1), 9825450. https://doi.org/10.1155/2024/9825450

Joelianto, E., Mandasari, M. I., Marpaung, D. B., Hafizhan, N. D., Heryono, T., Prasetyo, M. E., Dani, Tjahjani, S., Anggraeni, T., & Ahmad, I. (2024). Convolutional neural network-based real-time mosquito genus identification using wingbeat frequency: A binary and multiclass classification approach. Ecological Informatics, 80, 102495. https://doi.org/10.1016/j.ecoinf.2024.102495

Khysru, K., Wei, J., & Dang, J. (2022). Research on Tibetan Speech Recognition Based on the Am-do Dialect. Computers, Materials & Continua, 73(3), 4897–4907. https://doi.org/10.32604/cmc.2022.027591

Radford, A., Kim, J. W., Xu, T., Brockman, G., McLeavey, C., & Sutskever, I. (2022). Robust Speech Recognition via Large-Scale Weak Supervision (Version 1). arXiv. https://doi.org/10.48550/ARXIV.2212.04356

Rahman Sya’ban, D., Hamzah, A., & Susanti, E. (2022). Klasifikasi Buah Segar Dan Busuk Menggunakan Algoritma Convolutional Neural Network Dengan Tflite Sebagai Media Penerapan Model Machine Learning. PROSIDING SNAST, F7-16. https://doi.org/10.34151/prosidingsnast.v8i1.4180

Rehman, A., Kim, D., & Paul, A. (2023a). Convolutional Neural Network Model for Fire Detection in Real-Time Environment. Computers, Materials & Continua, 77(2), 2289–2307. https://doi.org/10.32604/cmc.2023.036435

Rehman, A., Kim, D., & Paul, A. (2023b). Convolutional Neural Network Model for Fire Detection in Real-Time Environment. Computers, Materials & Continua, 77(2), 2289–2307. https://doi.org/10.32604/cmc.2023.036435

Rendi Nurcahyo & Mohammad Iqbal. (2022). Pengenalan Emosi Pembicara Menggunakan Convolutional Neural Networks. Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi), 6(1), 115–122. https://doi.org/10.29207/resti.v6i1.3726

Soekarta, R., Nurdjan, N., & Syah, A. (2023). Klasifikasi Penyakit Tanaman Tomat Menggunakan Metode Convolutional Neural Network (CNN). Insect (Informatics and Security): Jurnal Teknik Informatika, 8(2), 143–151. https://doi.org/10.33506/insect.v8i2.2356

Song, Y. (2023). Chinese Speech Recognition System Based on Neural Network Acoustic Network Model. Procedia Computer Science, 228, 144–154. https://doi.org/10.1016/j.procs.2023.11.018

Utami, N. W., I Nyoman Purnama, & I Putu Restu Prajna. (2023). Klasifikasi Tanaman Upakara Adat Hindu Di Kebun Raya Eka Karya Bali Menggunakan Algoritma Convolutional Neural Network. Jurnal Informatika Teknologi Dan Sains (Jinteks), 5(4), 671–678. https://doi.org/10.51401/jinteks.v5i4.3416

Wang, H., Zhang, W.-Q., Suo, H., & Wan, Y. (2022). Multilingual Zero Resource Speech Recognition Base on Self-Supervise Pre-Trained Acoustic Models. 2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP), 11–15. https://doi.org/10.1109/ISCSLP57327.2022.10037938

Wang, N. Y.-H., Wang, H.-L. S., Wang, T.-W., Fu, S.-W., Lu, X., Wang, H.-M., & Tsao, Y. (2021). Improving the Intelligibility of Speech for Simulated Electric and Acoustic Stimulation Using Fully Convolutional Neural Networks. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 29, 184–195. https://doi.org/10.1109/TNSRE.2020.3042655

Wang, R., Lei, Z., Zhang, Z., & Gao, S. (2022). Dendritic Convolutional Neural Network. IEEJ Transactions on Electrical and Electronic Engineering, 17(2), 302–304. https://doi.org/10.1002/tee.23513

Wu, J., Gaur, Y., Chen, Z., Zhou, L., Zhu, Y., Wang, T., Li, J., Liu, S., Ren, B., Liu, L., & Wu, Y. (2023). On Decoder-Only Architecture For Speech-to-Text and Large Language Model Integration. 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 1–8. https://doi.org/10.1109/ASRU57964.2023.10389705

Downloads

PlumX Metrics

Published

31-03-2026

How to Cite

Anshor, Abdul Halim, and Aswan Supriyadi Sunge. 2026. “Pengembangan Model Prediksi Speech Recognition Dengan Algoritma Deep Learning Convolutional Neural Network”. Jurnal Saintekom : Sains, Teknologi, Komputer Dan Manajemen 16 (1):72-84. https://doi.org/10.33020/saintekom.v16i1.1020.

Issue

Vol. 16 No. 1 (2026): Maret 2026

Section

Articles

License

Copyright (c) 2026 Abdul Halim Anshor, Aswan Supriyadi Sunge

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Copyright :
By submitting manuscripts to Jurnal Saintekom : Sains, Teknologi, Komputer dan Manajemen, the author agrees with this policy. No specific document approval is required.

  1. The copyright in each article belongs to the author.
  2. Authors retain all their rights to the published work, not limited to the rights set forth in this page.
  3. Authors acknowledge that Saintekom Journal: Science, Technology, Computers and Management as the first to publish under the Creative Commons Attribution 4.0 International license (CC BY-SA).
  4. The author may submit the paper separately, arrange for non-exclusive distribution of the manuscript that has been published in this journal into other versions (e.g. sent to the author's institutional respository, publication into a book, etc.), by acknowledging that the manuscript has been first published Jurnal Saintekom : Sains, Teknologi, Komputer dan Manajemen;
  5. The author warrants that the article is original, written by the named author, has not been previously published, contains no unlawful statements, does not infringe the rights of others, is subject to copyright exclusively held by the author.
  6. If the article is jointly prepared by more than one author, each author submitting the manuscript warrants that he or she has been authorized by all co-authors to agree to copyright and license notices (agreements) on their behalf, and agrees to inform co-authors of the terms of this policy. Jurnal Saintekom : Sains, Teknologi, Komputer dan Manajemen will not be held liable for anything that may arise due to internal author disputes.

Lisensi :
Jurnal Saintekom : Sains, Teknologi, Komputer dan Manajemen  is published under the terms of the Creative Commons Attribution 4.0 International License (CC BY-SA). This license permits anyone to:.

  1. Share - copy and redistribute this material in any form or format;
  2. Adaptation - modify, alter, and create derivatives of this material for any purpose.
  3. Attribution - you must give appropriate credit, include a link to the license, and state that changes have been made. You may do this in any appropriate manner, but it does not imply that the licensor endorses you or your use.
  4. Similar Sharing - If you modify, alter, or create a derivative of this material, you must distribute your contribution under the same license as the original material.