<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">kaz44</journal-id><journal-title-group><journal-title xml:lang="ru">Вестник Университета Шакарима. Серия технические науки</journal-title><trans-title-group xml:lang="en"><trans-title>Bulletin of Shakarim University. Technical Sciences</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2788-7995</issn><issn pub-type="epub">3006-0524</issn><publisher><publisher-name>«Шәкәрім университеті» КеАҚ</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.53360/2788-7995-2024-4(16)-5</article-id><article-id custom-type="elpub" pub-id-type="custom">kaz44-1464</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>АВТОМАТИЗАЦИЯ И ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИ (ОРИГИНАЛЬНАЯ СТАТЬЯ)</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>AUTOMATION AND INFORMATION TECHNOLOGY (ORIGINAL ARTICLE)</subject></subj-group></article-categories><title-group><article-title>СВЕРТОЧНЫЕ НЕЙРОННЫЕ СЕТИ ДЛЯ ОБНАРУЖЕНИЯ РЕЧЕВОЙ АКТИВНОСТИ В ПОТОКЕ</article-title><trans-title-group xml:lang="en"><trans-title>CONVOLUTIONAL NEURAL NETWORKS IN DETECTING SPEECH ACTIVITY IN A STREAM</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Таубакабыл</surname><given-names>Н. М.</given-names></name><name name-style="western" xml:lang="en"><surname>Taubakabyl</surname><given-names>N. M.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Нурлыбек Мурабекулы Таубакабыл – магистрант </p><p>010000, Республика Казахстан, г. Астана, пр. Мәңгілік Ел, С1 </p></bio><bio xml:lang="en"><p>Nurlybek Muratbekuly Taubakabyl – Master's Student </p><p>010000, Republic of Kazakhstan, Astana, Mangilik El Avenue, С1 </p></bio><email xlink:type="simple">tbkbl.03@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru">Астана IT Университет<country>Казахстан</country></aff><aff xml:lang="en">Astana IT University<country>Kazakhstan</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2024</year></pub-date><pub-date pub-type="epub"><day>27</day><month>12</month><year>2024</year></pub-date><volume>1</volume><issue>4(16)</issue><fpage>33</fpage><lpage>40</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Таубакабыл Н.М., 2025</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="ru">Таубакабыл Н.М.</copyright-holder><copyright-holder xml:lang="en">Taubakabyl N.M.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://tech.vestnik.shakarim.kz/jour/article/view/1464">https://tech.vestnik.shakarim.kz/jour/article/view/1464</self-uri><abstract><p>Исследование, представленное в этой статье, посвящено разработке системы обнаружения речевой активности в аудио потоках с использованием сверточных нейронных сетей (CNNS). Распознавание речевой активности играет решающую роль во многих современных приложениях, таких как голосовые помощники, коммуникационные платформы в режиме реального времени и службы автоматической транскрипции. В исследовании обобщены результаты девяти ключевых исследований, демонстрирующих эффективность CNNS в обработке сложных аудиоданных, отделении речевых сигналов от шума и повышении общей точности обнаружения.Исследование подчеркивает архитектурные преимущества моделей deep CNN, таких как VGG, ResNet и AlexNet, подчеркивая их способность улавливать сложные звуковые характеристики и повышать производительность в различных средах. В исследовании также рассматриваются такие методы, как увеличение объема данных и алгоритмы оптимизации, которые еще больше повышают надежность и эффективность этих моделей.Оценивая эффективность различных архитектур CNN и сравнивая различные оценочные показатели, исследователи выявляют потенциальные области для будущих исследований, такие как оптимизация моделей CNN для приложений реального времени и изучение гибридных архитектур. В целом, это исследование дает ценную информацию о состоянии распознавания речевой активности на основе CNN и его значении для реальных приложений.</p></abstract><trans-abstract xml:lang="en"><p>The research presented in this article focuses on the development of a system for detecting speech activity in audio streams using convolutional neural networks (CNNs). Speech activity detection plays a crucial role in many modern applications, such as voice-activated assistants, real-time communication platforms, and automated transcription services. The study synthesizes findings from nine key studies, demonstrating the effectiveness of CNNs in handling complex audio data, isolating speech signals from noise, and improving overall detection accuracy.The research emphasizes the architectural advantages of deep CNN models, such as VGG, ResNet, and AlexNet, highlighting their ability to capture intricate audio features and improve performance across various environments. The study also explores techniques like data augmentation and optimization algorithms, which further enhance the robustness and efficiency of these models.By evaluating the effectiveness of different CNN architectures and comparing various evaluation metrics, the research identifies potential areas for future exploration, such as optimizing CNN models for real-time applications and exploring hybrid architectures. Overall, this research offers valuable insights into the state of CNN-based speech activity detection and its implications for real-world applications.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>Сверточные нейронные сети</kwd><kwd>Обнаружение речевой активности</kwd><kwd>аудиопотоки</kwd><kwd>VGG</kwd><kwd>ResNet</kwd><kwd>AlexNet</kwd><kwd>Общение в реальном времени</kwd><kwd>Голосовые помощники</kwd><kwd>Распознавание речи</kwd><kwd>Обработка звука</kwd></kwd-group><kwd-group xml:lang="en"><kwd>Convolutional Neural Networks</kwd><kwd>Speech Activity Detection</kwd><kwd>Audio Streams</kwd><kwd>VGG</kwd><kwd>ResNet</kwd><kwd>AlexNet</kwd><kwd>Real-time Communication</kwd><kwd>Voice-activated Assistants</kwd><kwd>Speech Recognition</kwd><kwd>Audio Processing</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Deep speech 2: End-to-end speech recognition in English and Mandarin / D. Amodei et al // Computation and Language (cs.CL). – 2015. https://doi.org/10.48550/arXiv.1512.02595.</mixed-citation><mixed-citation xml:lang="en">Deep speech 2: End-to-end speech recognition in English and Mandarin / D. Amodei et al // Computation and Language (cs.CL). – 2015. https://doi.org/10.48550/arXiv.1512.02595.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">CNN architectures for large-scale audio classification / S. Hershey et al // In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). – 2017. – Р. 131-135. https://arxiv.org/pdf/1609.09430.</mixed-citation><mixed-citation xml:lang="en">CNN architectures for large-scale audio classification / S. Hershey et al // In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). – 2017. – Р. 131-135. https://arxiv.org/pdf/1609.09430.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Very deep multilingual convolutional neural networks for LVCSR / T. Sercu et al // arXiv preprint arXiv:1509.08967. – 2016. https://arxiv.org/pdf/1509.08967.</mixed-citation><mixed-citation xml:lang="en">Very deep multilingual convolutional neural networks for LVCSR / T. Sercu et al // arXiv preprint arXiv:1509.08967. – 2016. https://arxiv.org/pdf/1509.08967.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Luo Y. Conv-tasnet: Surpassing ideal time-frequency magnitude masking for speech separation / Y. Luo, N. Mesgarani // IEEE/ACM Transactions on Audio, Speech, and Language Processing. – 2018. – № 27(8). – Р. 1256-1266. https://arxiv.org/pdf/1809.07454.</mixed-citation><mixed-citation xml:lang="en">Luo Y. Conv-tasnet: Surpassing ideal time-frequency magnitude masking for speech separation / Y. Luo, N. Mesgarani // IEEE/ACM Transactions on Audio, Speech, and Language Processing. – 2018. – № 27(8). – Р. 1256-1266. https://arxiv.org/pdf/1809.07454.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Grill T. Two convolutional neural networks for bird detection in audio signals / T. Grill, J. Schlüter, // In 2017 25th European Signal Processing Conference (EUSIPCO). – 2017. – Р. 1764-1768. https://www.ofai.at/~jan.schlueter/pubs/2017_eusipco.pdf.</mixed-citation><mixed-citation xml:lang="en">Grill T. Two convolutional neural networks for bird detection in audio signals / T. Grill, J. Schlüter, // In 2017 25th European Signal Processing Conference (EUSIPCO). – 2017. – Р. 1764-1768. https://www.ofai.at/~jan.schlueter/pubs/2017_eusipco.pdf.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Joint training of deep neural networks for audio-visual automatic speech recognition / Y. Qian et al // IEEE/ACM Transactions on Audio, Speech, and Language Processing. – 2017. – № 25(12). – Р. 2381-2393. https://arxiv.org/pdf/2205.13293.</mixed-citation><mixed-citation xml:lang="en">Joint training of deep neural networks for audio-visual automatic speech recognition / Y. Qian et al // IEEE/ACM Transactions on Audio, Speech, and Language Processing. – 2017. – № 25(12). – Р. 2381-2393. https://arxiv.org/pdf/2205.13293.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Vincent E. Performance measurement in blind audio source separation / E. Vincent, R. Gribonval, C. Févotte // IEEE Transactions on Audio, Speech, and Language Processing. – 2006. – № 14(4). – Р. 1462-1469. https://inria.hal.science/inria-00544230/document.</mixed-citation><mixed-citation xml:lang="en">Vincent E. Performance measurement in blind audio source separation / E. Vincent, R. Gribonval, C. Févotte // IEEE Transactions on Audio, Speech, and Language Processing. – 2006. – № 14(4). – Р. 1462-1469. https://inria.hal.science/inria-00544230/document.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Convolutional neural networks for speech recognition / O. Abdel-Hamidet al // IEEE/ACM Transactions on Audio, Speech, and Language Processing. – 2014. – № 22(10). – Р. 1533-1545. https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/CNN_ASLPTrans2-14.pdf</mixed-citation><mixed-citation xml:lang="en">Convolutional neural networks for speech recognition / O. Abdel-Hamidet al // IEEE/ACM Transactions on Audio, Speech, and Language Processing. – 2014. – № 22(10). – Р. 1533-1545. https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/CNN_ASLPTrans2-14.pdf</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Accelerating very deep convolutional networks for classification and detection / X. Zhang et al // IEEE Transactions on Pattern Analysis and Machine Intelligence. – 2016. – № 38(10). – Р. 1943-1955. https://arxiv.org/pdf/1505.06798.</mixed-citation><mixed-citation xml:lang="en">Accelerating very deep convolutional networks for classification and detection / X. Zhang et al // IEEE Transactions on Pattern Analysis and Machine Intelligence. – 2016. – № 38(10). – Р. 1943-1955. https://arxiv.org/pdf/1505.06798.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">VanderPlas J. Python Data Science Handbook / J. VanderPlas // Essential Tools for Working with Data. O'Reilly Media. https://jakevdp.github.io/PythonDataScienceHandbook.</mixed-citation><mixed-citation xml:lang="en">VanderPlas J. Python Data Science Handbook / J. VanderPlas // Essential Tools for Working with Data. O'Reilly Media. https://jakevdp.github.io/PythonDataScienceHandbook.</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
