bsuirДоклады БГУИРDoklady BGUIR1729-76482708-0382БГУИР10.35596/1729-7648-2025-23-6-96-102bsuir-4253Research ArticleСтатьиДетектирование бокового амиотрофического склероза на основе акустического анализа голоса с использованием библиотеки openSMILEDetection of Amyotrophic Lateral Sclerosis Based on Acoustic Voice Analysis Using the openSMILE LibraryМихневичА. В.MikhnevichA. V.

асп. каф. электронных вычислительных средств

220013, Минск, ул. П. Бровки, 6

Postgraduate at the Department of Electronic Computing Facilities

220013, Minsk, P. Brovki St., 6

ВашкевичМ. И.VashkevichM. I.

Вашкевич Максим Иосифович, д-р техн. наук, проф. каф. электронных вычислительных средств

220013, Минск, ул. П. Бровки, 6

Тел.: +375 17 293-84-78

Vashkevich Maxim Iosifovich, Dr. Sci. (Tech.), Professor at the Department of Electronic Computing Facilities

220013, Minsk, P. Brovki St., 6

Tel.: +375 17 293-84-78

vashkevich@bsuir.byБелорусский государственный университет информатики и радиоэлектроникиBelarusian State University of informatics and Radioelectronics20252512202523696102Copyright © Михневич А.В., Вашкевич М.И., 20252025Михневич А.В., Вашкевич М.И.Mikhnevich A.V., Vashkevich M.I.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://doklady.bsuir.by/jour/article/view/4253

Рассмотрена задача автоматического выявления признаков бокового амиотрофического склероза на основе анализа акустических характеристик голосового сигнала. Для извлечения функциональных акустических признаков голоса использовалась библиотека openSMILE с конфигурацией ComParE_2016. В качестве исходных данных использовались аудиозаписи из голосовой базы Minsk2020_ALS, включающей записи как здоровых пациентов, так и пациентов с боковым амиотрофическим склерозом. Проведены сравнение голосовых признаков между группами с использованием непараметрического критерия Манна – Уитни и FDR-коррекции множественных сравнений и раздельный анализ по полу. Выполнен эксперимент по классификации голосовых сигналов с использованием вложенной процедуры перекрестной проверки. Получены классификаторы, имеющие вероятность правильного обнаружения 75,0 % (для мужских голосов) и 74,2 % (для женских голосов). Выявлены статистически значимые акустические параметры, которые могут быть полезны в задачах автоматизированной диагностики и мониторинга бокового амиотрофического склероза.

This paper examines the problem of automatically detecting signs of amyotrophic lateral sclerosis based on the analysis of the acoustic characteristics of a voice signal. The openSMILE library with the ComParE_2016 configuration was used to extract functional acoustic features of the voice. Audio recordings from the Minsk2020_ALS voice database, which includes recordings of both healthy patients and patients with amyotrophic lateral sclerosis, were used as input. Voice features were compared between groups using the nonparametric Mann–Whitney test and FDR correction for multiple comparisons, with separate analysis by gender. An experiment on classifying voice signals was conducted using a nested cross-validation procedure. The resulting classifiers had a correct detection probability of 75.0 % (for male voices) and 74.2 % (for female voices). Statistically significant acoustic parameters that may be useful in automated diagnostics and monitoring of amyotrophic lateral sclerosis were identified.

боковой амиотрофический склерозopenSMILEречевые признакиакустический анализстатистикаFDR-коррекциamyotrophic lateral sclerosisopenSMILEspeech featuresacoustic analysisstatisticsFDR correctionReferencesBowden M., Beswick E., Tam J., Perry D., Smith A., Newton J., et al. (2023) A Systematic Review and Narrative Analysis of Digital Speech Biomarkers in Motor Neuron Disease. NPJ Digital Medicine. 6 (1), 1–19.Bowden M., Beswick E., Tam J., Perry D., Smith A., Newton J., et al. (2023) A Systematic Review and Narrative Analysis of Digital Speech Biomarkers in Motor Neuron Disease. NPJ Digital Medicine. 6 (1), 1–19.Norel R., Pietrowicz M., Agurto C., Rishoni S., Cecchi G. (2018) Detection of Amyotrophic Lateral Sclerosis (ALS) Via Acoustic Analysis. Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH). 377–381.Norel R., Pietrowicz M., Agurto C., Rishoni S., Cecchi G. (2018) Detection of Amyotrophic Lateral Sclerosis (ALS) Via Acoustic Analysis. Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH). 377–381.Folgado D., Rocha P. S., Matias P., Liebeatrau D., Nunes F., Rocha T., et al. (2025) HomeSenseALS: A Mobile Sensing and Self-Monitoring System to Monitor Patients with ALS in Everyday Life. ACM Transactions on Computing for Healthcare. 25 (3), 1–32.Folgado D., Rocha P. S., Matias P., Liebeatrau D., Nunes F., Rocha T., et al. (2025) HomeSenseALS: A Mobile Sensing and Self-Monitoring System to Monitor Patients with ALS in Everyday Life. ACM Transactions on Computing for Healthcare. 25 (3), 1–32.An K., Kim M., Teplansky K., Green J., Campbell T., Yunusova Y., et al. (2018) Automatic Early Detection ofAmyotrophic Lateral Sclerosis from Intelligible Speech Using Convolutional Neural Networks. Proceedings of Interspeech. 1913–1917.An K., Kim M., Teplansky K., Green J., Campbell T., Yunusova Y., et al. (2018) Automatic Early Detection ofAmyotrophic Lateral Sclerosis from Intelligible Speech Using Convolutional Neural Networks. Proceedings of Interspeech. 1913–1917.Illa A., Patel D., Yamini B. K., Veeramani P.-K., Polavarapu K., Nashi S., et al. (2018) Comparison of Speech Tasks for Automatic Classification of Patients with Amyotrophic Lateral Sclerosis and Healthy Subjects. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 6014–6018.Illa A., Patel D., Yamini B. K., Veeramani P.-K., Polavarapu K., Nashi S., et al. (2018) Comparison of Speech Tasks for Automatic Classification of Patients with Amyotrophic Lateral Sclerosis and Healthy Subjects. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 6014–6018.Yunusova Y., Green J. R., Greenwood L., Wang J., Pattee G. L., Zinman L. (2012) Tongue Movements andTheir Acoustic Consequences in Amyotrophic Lateral Sclerosis. Journal of Speech, Language, and Hearing Research. 55 (3), 673–687.Yunusova Y., Green J. R., Greenwood L., Wang J., Pattee G. L., Zinman L. (2012) Tongue Movements andTheir Acoustic Consequences in Amyotrophic Lateral Sclerosis. Journal of Speech, Language, and Hearing Research. 55 (3), 673–687.Eyben F., Wӧllmer M., Schuller B. (2010) openSMILE: The Munich Versatile and Fast Open-Source Audio Feature Extractor. Proceedings of the 18th ACM International Conference on Multimedia. 1459–1462.Eyben F., Wӧllmer M., Schuller B. (2010) openSMILE: The Munich Versatile and Fast Open-Source Audio Feature Extractor. Proceedings of the 18th ACM International Conference on Multimedia. 1459–1462.Bocklet T., Steidl S., Nӧth E., Skodda S. (2013) Automatic Evaluation of Parkinson’s Speech-Acoustic, Prosodic and Voice-Related Cues. Proceedings of Interspeech. 1149–1153.Bocklet T., Steidl S., Nӧth E., Skodda S. (2013) Automatic Evaluation of Parkinson’s Speech-Acoustic, Prosodic and Voice-Related Cues. Proceedings of Interspeech. 1149–1153.Vashkevich M., Rushkevich Yu. (2021) Classification of ALS Patients Based on Acoustic Analysis of Sustained Vowel Phonations. Biomedical Signal Processing and Control. 65, 1–14.Vashkevich M., Rushkevich Yu. (2021) Classification of ALS Patients Based on Acoustic Analysis of Sustained Vowel Phonations. Biomedical Signal Processing and Control. 65, 1–14.Minsk2020_ALS_database: Classification of ALS Patients Based on Acoustic Analysis of Sustained Vowel Phonations. GitHub. Available: https://github.com/Mak-Sim/Minsk2020_ALS_database (Accessed 6 October 2025).Minsk2020_ALS_database: Classification of ALS Patients Based on Acoustic Analysis of Sustained Vowel Phonations. GitHub. Available: https://github.com/Mak-Sim/Minsk2020_ALS_database (Accessed 6 October 2025).Hermansky H., Morgan N. (1994) RASTA Processing of Speech. IEEE Transactions on Speech and Audio Processing. 2 (4), 578–589.Hermansky H., Morgan N. (1994) RASTA Processing of Speech. IEEE Transactions on Speech and Audio Processing. 2 (4), 578–589.Hastie T., Tibshirani R., Friedman J. H. (2009) The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer.Hastie T., Tibshirani R., Friedman J. H. (2009) The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer.

The authors declare that there are no conflicts of interest present.