<?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">sapi</journal-id><journal-title-group><journal-title xml:lang="ru">Системный анализ и прикладная информатика</journal-title><trans-title-group xml:lang="en"><trans-title>«System analysis and applied information science»</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2309-4923</issn><issn pub-type="epub">2414-0481</issn><publisher><publisher-name>Belarusian National Technical University</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.21122/2309-4923-2025-1-38-43</article-id><article-id custom-type="elpub" pub-id-type="custom">sapi-729</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>Обработка информации и принятие решений</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>Data processing and decision–making</subject></subj-group></article-categories><title-group><article-title>Отбор признаков на основе техники переноса обучения для классификации эмоций в речи с помощью полносвязной нейронной сети прямого распространения</article-title><trans-title-group xml:lang="en"><trans-title>Transfer learning based feature selection for feedforward neural network for speech emotion classifier</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>Краснопрошин</surname><given-names>Д. B.</given-names></name><name name-style="western" xml:lang="en"><surname>Krasnoproshin</surname><given-names>D. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Краснопрошин Д.В., аспирант каф. электронных вычислительных средств</p><p>г. Минск</p></bio><bio xml:lang="en"><p>Krasnoproshin D.V., PhD Student at the Department of Electronic Computing Facilities</p><p>Minsk</p></bio><email xlink:type="simple">daniil.krasnoproshin@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Вашкевич</surname><given-names>М. И.</given-names></name><name name-style="western" xml:lang="en"><surname>Vashkevich</surname><given-names>M. I.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Вашкевич М.И., д-р техн. наук, проф. каф. электронных вычислительных средств</p><p>г. Минск</p></bio><bio xml:lang="en"><p>Vashkevich M. I., PhD, Professor at the Department of Electronic Computing Facilities</p><p>Minsk</p></bio><email xlink:type="simple">vashkevich@bsuir.by</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Белорусский государственный университет информатики и радиоэлектроники</institution><country>Беларусь</country></aff><aff xml:lang="en"><institution>Belarusian State University of Informatics and Radioelectronics</institution><country>Belarus</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>07</day><month>04</month><year>2025</year></pub-date><volume>0</volume><issue>1</issue><fpage>38</fpage><lpage>43</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Краснопрошин Д.B., Вашкевич М.И., 2025</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="ru">Краснопрошин Д.B., Вашкевич М.И.</copyright-holder><copyright-holder xml:lang="en">Krasnoproshin D.V., Vashkevich M.I.</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://sapi.bntu.by/jour/article/view/729">https://sapi.bntu.by/jour/article/view/729</self-uri><abstract><p>В работе исследуется задача распознавания эмоций в речи с помощью метода проектирования и отбора речевых признаков. В качестве исходных аудио признаков использовались мел-частотные кепстральные коэффициенты. В работе предлагается подход, в основе которого лежит идея переноса обучения, заключается в использовании метода пошагового исключения признаков при помощи статистических моделей – классификаторов. Отобранное подмножество признаков затем используется для обучения полносвязных нейронных сетей прямого распространения. Такой подход позволяет значительно уменьшить размер исходного признакового пространства и одновременно повысить качество предсказаний моделей. В качестве наборов данных для постановки экспериментов были использованы TESS и RAVDESS. Метрикой оценки качества классификаторов послужила невзвешенная средняя полнота (unweighted average recall – UAR). Результаты экспериментов являются многообещающими (UAR для TESS = 82 %, UAR для RAVDESS = 53 %), тем самым демонстрируя перспективность предложенного подхода к задаче классификации эмоций по речи.</p></abstract><trans-abstract xml:lang="en"><p>This work discusses speech emotion recognition via custom feature engineering and feature selection techniques using mel-frequency cepstral coefficients as initial audio features. Proposed transfer learning approach consist in employing the backward-step selection algorithm for feature selection using statistical learning classifiers, the obtained subset of features than subsequently used to train feedforward neural networks. This technique allowed us to significantly reduce initial feature vector size while increasing models’ prediction quality. We used TESS and RAVDESS datasets to estimate the performance of proposed method. To evaluate the quality of the model, unweighted average recall (UAR) was used. Experimental results demonstrate promising accuracy (UAR = 82 % for TESS and UAR = 53 % for RAVDESS), showcasing the potential of this approach for applications like virtual agents, voice assistants and mental health diagnostics.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>распознавание эмоций</kwd><kwd>отбор признаков</kwd><kwd>МЧКК</kwd><kwd>нейронные сети</kwd><kwd>линейный дискриминантный анализ</kwd><kwd>метод опорных векторов</kwd></kwd-group><kwd-group xml:lang="en"><kwd>speech emotion recognition</kwd><kwd>feature selection</kwd><kwd>MFCC</kwd><kwd>neural networks</kwd><kwd>linear discriminant analysis</kwd><kwd>support vector machine</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">Issa D. Speech emotion recognition with deep convolutional neural networks / D. Issa, M. Demirci, A. Yazici // Biomedical Signal Processing and Control. – 2020. – Vol. 59. – Pp. 1-11.</mixed-citation><mixed-citation xml:lang="en">Issa D. Speech emotion recognition with deep convolutional neural networks / D. Issa, M. Demirci, A. Yazici // Biomedical Signal Processing and Control. – Vol. 59. – 2020. – P. 1-11.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Baruah M., Banerjee B. Speech emotion recognition via generation using an attention-based variational recurrent neural network // Proceedings of the INTERSPEECH. – 2022. – Pp. 4710-4714.</mixed-citation><mixed-citation xml:lang="en">Baruah M., Banerjee B. Speech emotion recognition via generation using an attention-based variational recurrent neural network // Proceedings of the INTERSPEECH. – 2022. – P. 4710-4714.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Краснопрошин Д.В., Вашкевич М.И. Метод распознавания эмоций в речевом сигнале с использованием машины опорных векторов и надсегментных акустических признаков // Доклады БГУИР. – 2024. – Т. 22. – № 3. – С. 93-100.</mixed-citation><mixed-citation xml:lang="en">Krasnoproshin D.V., Vashkevich M.I. Speech emotion recognition method based on support vector machine and suprasegmental acoustic features // Doklady BGUIR. – 2024. – Vol. 22. – № 3. – P. 93-100. (In Russ.)</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Флах П. Машинное обучение. Наука и искусство построения алгоритмов, которые извлекают знания из данных / пер. с англ. А.А. Слинкина. М.: ДМК Пресс, 2015. 400 с.</mixed-citation><mixed-citation xml:lang="en">Flach P. Machine Learning: The Art and Science of Algorithms that Make Sense of Data. // Cambridge University Press, 2012. – 410 p.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Tsanas A. et al. Novel speech signal processing algorithms for high-accuracy classification of Parkinson's disease // IEEE transactions on biomedical engineering. – 2012. – Т. 59. – № 5. – P. 1264-1271.</mixed-citation><mixed-citation xml:lang="en">Tsanas A. et al. Novel speech signal processing algorithms for high-accuracy classification of Parkinson's disease // IEEE transactions on biomedical engineering. – 2012. – Vol. 59. – № 5. – P. 1264-1271.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Huang S. H. Supervised feature selection: A tutorial //Artif. Intell. Res. – 2015. – Т. 4. – № 2. – С. 22-37.</mixed-citation><mixed-citation xml:lang="en">Huang S. H. Supervised feature selection: A tutorial //Artif. Intell. Res. – 2015. – Vol. 4. – № 2. – P. 22-37.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Джеймс Г. и др. Введение в статистическое обучение с примерами на языке R / Г. Джеймс, Д. Уиттон, Т. Хасти, Р. Тибширани //М.: ДМК Пресс, 2016. – 450 с.</mixed-citation><mixed-citation xml:lang="en">James G. et al. An Introduction to Statistical Learning: With Applications in R / G. James, T. Hastie, R. Tibshirani, D. Witten // Springer, 2013. – 426 p.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Pichora-Fuller, M. Kathleen, and Kate Dupuis. Toronto Emotional Speech Set (TESS). Borealis, 2020. https://doi.org/10.5683/SP2/E8H2MF</mixed-citation><mixed-citation xml:lang="en">Pichora-Fuller, M. Kathleen, and Kate Dupuis. Toronto Emotional Speech Set (TESS). Borealis, 2020. https://doi.org/10.5683/SP2/E8H2MF</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Livingstone, Steven R., and Frank A. Russo. The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS). Zenodo, 2018. https://doi.org/10.5281/zenodo.1188975</mixed-citation><mixed-citation xml:lang="en">Livingstone, Steven R., and Frank A. Russo. The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS). Zenodo, 2018. https://doi.org/10.5281/zenodo.1188975.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Luna-Jiménez C. Multimodal emotion recognition on RAVDESS dataset using transfer learning / C. Luna-Jiménez, Griol, Z. Callejas, R. Kleinlein, J. M. Montero, F. Fernández-Martínez // Sensors. – 2021. – Vol. 22. – Pp. 1–29.</mixed-citation><mixed-citation xml:lang="en">Luna-Jiménez C. Multimodal emotion recognition on RAVDESS dataset using transfer learning / C. Luna-Jiménez, Griol, Z. Callejas, R. Kleinlein, J. M. Montero, F. Fernández-Martínez. Sensors. – 2021. – Vol. 22. – P. 1–29.</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>
