izmertechИзмерительная техникаIzmeritel`naya Tekhnika0368-10252949-5237ФГУП "ВНИИФТРИ"10.32446/0368-1025it.2023-10-63-69izmertech-2047Research ArticleАКУСТИЧЕСКИЕ ИЗМЕРЕНИЯACOUSTIC MEASUREMENTSМера различий речевых сигналов по тембру голосаA measure of differences in speech signals by the voice timbrehttps://orcid.org/0000-0003-3045-3337СавченкоВ. В.SavchenkoV. V.

Владимир Васильевич Савченко - доктор технических наук, профессор.

Нижний Новгород

Vladimir V. Savchenko

Nizhny Novgorod

vvsavchenko@yandex.ruНациональный исследовательский университет «Высшая школа экономики»РоссияNational Research University Higher School of EconomicsRussian Federation2023171120230106369Copyright © ФГУП "ВНИИФТРИ", 20232023ФГУП "ВНИИФТРИ"ФГУП "ВНИИФТРИ"https://www.izmt.ru/jour/about/submissions#copyrightNoticehttps://www.izmt.ru/jour/article/view/2047

Описана ключевая проблема в области речевых технологий – оптимизация обработки речевого сигнала в условиях априорной неопределённости его тонкой структуры. Рассмотрена задача автоматического (объективного) анализа тембра голоса диктора по речевому сигналу конечной длительности. Для решения этой задачи предложен универсальный теоретико-информационный подход. На основе дивергенции Кульбака-Лейблера получено выражение для асимптотически оптимальной решающей статистики различения речевых сигналов по тембру голоса. Указано на острую проблему при практической реализации данной статистики – синхронизацию последовательности наблюдений с основным тоном речевых сигналов. Для преодоления описанной проблемы предложена объективная мера тембровых различий речевых сигналов в терминах акустической теории речеобразования и её модели голосового тракта диктора типа «акустическая труба». Рассмотрены возможности практической реализации новой меры на базе адаптивного рекурсивного фильтра. Поставлен и проведён натурный эксперимент. По его результатам подтверждены два основных свойства предложенной меры – высокая чувствительность к различиям речевых сигналов по тембру голоса и инвариантность к частоте основного тона. Полученные результаты можно применять при проектировании и исследовании систем цифровой обработки речи с настройкой на голос диктора, например систем цифровой передачи речи, биометрических и биомедицинских систем и др.

This research relates to the field of speech technologies, where the key problem is the optimization of speech signal processing under conditions of a priori uncertainty of its fine structure. The task of automatic (objective) analysis of voice timbre using a speech signal of finite duration is considered. It is proposed to use a universal information-theoretic approach to solve it. Based on the Kullback-Leibler divergence, an expression is obtained for the asymptotically optimal decision statistic for distinguishing speech signals by voice timbre. Pointed to an acute problem in its practical implementation, namely: synchronization of the sequence of observations with the main tone of speech signals. To overcome the described problem, an objective measure of timbre differences in speech signals is proposed in terms of the acoustic theory of speech production and its model of the speaker’s vocal tract of the “acoustic trumpet” type. The possibilities of practical implementation of a new measure based on an adaptive recursive are considered. A full-scale experiment was set up and carried out. According to its results, two main properties of the proposed measure were confirmed: high sensitivity to differences in speech signals in terms of voice timbre and, at the same time, invariance with respect to the pitch frequency. The results obtained can be used in the design and research of digital speech processing systems tuned to the speaker’s voice, for example, digital speech transmission systems, biometric, biomedical systems, etc.

акустические измеренияакустика речиречевой сигналосновной тончастота основного тонаголосовой трактчистополюсная модельметод Бергаacoustic measurementsspeech acousticsspeech signalpitchvocal tractall-pole modelBerg's methodReferencesZhao R., Erleke E., Wang L., Huang J., Chen, Z., The Effects of Timbre on Voice Interaction, in Cross-Cultural Design: HCII 2023. Lecture Notes in Computer Science, ed. Rau P-L. P., Springer, Cham, 2023, vol. 14023. https://doi.org/10.1007/978-3-031-35939-2_12Zhao R., Erleke E., Wang L., Huang J., Chen, Z., The Effects of Timbre on Voice Interaction, in Cross-Cultural Design: HCII 2023. Lecture Notes in Computer Science, ed. Rau P-L. P., Springer, Cham, 2023, vol. 14023. https://doi.org/10.1007/978-3-031-35939-2_12Ando Y., Temporal and Spatial Features of Speech Signals, in Signal Processing in Auditory Neuroscience, Academic Press, 2019, pp. 81–101. https://doi.org/10.1016/B978-0-12-815938-5.00009-1Ando Y., Temporal and Spatial Features of Speech Signals, in Signal Processing in Auditory Neuroscience, Academic Press, 2019, pp. 81–101. https://doi.org/10.1016/B978-0-12-815938-5.00009-1Ternström S., Applied Sciences, 2023, vol. 13, no. 6, 3514. https://doi.org/10.3390/app13063514Ternström S., Applied Sciences, 2023, vol. 13, no. 6, 3514. https://doi.org/10.3390/app13063514Song W., Yue Y., Zhang Ya-jie et al., Multi-speaker Multistyle Speech Synthesis with Timbre and Style Disentanglement, in Man-Machine Speech Communication: NCMMSC 2022. Communications in Computer and Information Science, eds. Zhenhua L., Jianqing G., Kai Y., Jia J., 2022, vol. 1765, Springer, Singapore. https://doi.org/10.1007/978-981-99-2401-1_12Song W., Yue Y., Zhang Ya-jie et al., Multi-speaker Multistyle Speech Synthesis with Timbre and Style Disentanglement, in Man-Machine Speech Communication: NCMMSC 2022. Communications in Computer and Information Science, eds. Zhenhua L., Jianqing G., Kai Y., Jia J., 2022, vol. 1765, Springer, Singapore. https://doi.org/10.1007/978-981-99-2401-1_12Jialu L., Hasegawa-Johnson M., McElwain N. L., Speech Communication, 2021, vol. 133, pp. 41–61. https://doi.org/10.1016/j.specom.2021.07.010Jialu L., Hasegawa-Johnson M., McElwain N. L., Speech Communication, 2021, vol. 133, pp. 41–61. https://doi.org/10.1016/j.specom.2021.07.010Savchenko V. V. Radioelectronics and Communications Systems, 2021, vol. 64, no. 11, pp. 592–603. https://doi.org/10.3103/S0735272721110030Savchenko V. V. Radioelectronics and Communications Systems, 2021, vol. 64, no. 11, pp. 592–603. https://doi.org/10.3103/S0735272721110030Савченко А. В., Савченко В. В. Способ автоматического обновления биометрических персональных данных в режиме онлайн по речевому сигналу пользователя биометрической системы // Измерительная техника. 2021. № 11. С. 60–66. https://doi.org/10.32446/0368-1025it.2021-11-60-66Savchenko A. V., Savchenko V. V., Measurement Techniques, 2022, vol. 64, no. 4, рр. 928–935. https://doi.org/10.1007/s11018-022-02025-4Wei Y., Gan L., Huang X., Frontiers in Psychology, 2022, vol. 13, 869475. https://doi.org/10.3389/fpsyg.2022.869475Wei Y., Gan L., Huang X., Frontiers in Psychology, 2022, vol. 13, 869475. https://doi.org/10.3389/fpsyg.2022.869475Xue J., Zhou H., Song H., Wu B., Shi L., Speech Communication, 2023, vol. 147, pp. 41–50. https://doi.org/10.1016/j.specom.2023.01.001Xue J., Zhou H., Song H., Wu B., Shi L., Speech Communication, 2023, vol. 147, pp. 41–50. https://doi.org/10.1016/j.specom.2023.01.001Li J., Zhang L. and Qiu Z., 5th International Conference on Intelligent Control, Measurement and Signal Processing (ICMSP), Chengdu, China, 2023, pp. 833–837. https://doi.org/10.1109/ICMSP58539.2023.10171030Li J., Zhang L. and Qiu Z., 5th International Conference on Intelligent Control, Measurement and Signal Processing (ICMSP), Chengdu, China, 2023, pp. 833–837. https://doi.org/10.1109/ICMSP58539.2023.10171030Igras-Cybulska M., Hekiert D., Cybulski A. et al., Work-inProgress. 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), Shanghai, China, 2023, pp. 355–359. https://doi.org/10.1109/VRW58643.2023.00079Igras-Cybulska M., Hekiert D., Cybulski A. et al., Work-inProgress. 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), Shanghai, China, 2023, pp. 355–359. https://doi.org/10.1109/VRW58643.2023.00079Cui S., Li E. and Kang X., 2020 IEEE International Conference on Multimedia and Expo (ICME), London, UK, 2020, pp. 1–6. https://doi.org/10.1109/ICME46284.2020.9102765Cui S., Li E. and Kang X., 2020 IEEE International Conference on Multimedia and Expo (ICME), London, UK, 2020, pp. 1–6. https://doi.org/10.1109/ICME46284.2020.9102765Gupta S., Fahad M. S. & Deepak A., Multimedia Tools and Applications, 2020, vol. 79, pp. 23347–23365. https://doi.org/10.1007/s11042-020-09068-1Gupta S., Fahad M. S. & Deepak A., Multimedia Tools and Applications, 2020, vol. 79, pp. 23347–23365. https://doi.org/10.1007/s11042-020-09068-1Dai B., Zahorian St., Journal of The Acoustical Society of America, 1998, vol. 104, 1805. https://doi.org/10.1121/1.423591Dai B., Zahorian St., Journal of The Acoustical Society of America, 1998, vol. 104, 1805. https://doi.org/10.1121/1.423591Захарьев В. А., Петровский А. А. Методы параметризации речевого сигнала на основе анализа, синхронизированного с частотой основного тона в системах конверсии голоса // Наука – образованию, производству, экономике: материалы 11-й Международной научно-технической конференции. Минск: БНТУ, 2013. Т. 1. С. 203–204.Zakhar’ev V. A., Petrovskii A. A. Metody parametrizatsii rechevogo signala na osnove analiza, sinkhronizirovannogo s chastotoi osnovnogo tona v sistemakh konversii golosa, Proceedings of the 11 International Scientific and Technical Conference “Nauka – obrazovaniyu, proizvodstvu, ekonomike”, Minsk, BNTU, 2013, vol. 1, рр. 203– 204 (In Russ.)Савченко В. В., Савченко Л. В. Субоптимальный алгоритм измерения частоты основного тона с использованием дискретного фурье-преобразования речевого сигнала // Радиотехника и электроника. 2023. Т. 68. № 7. С 660–668. https://doi.org/10.31857/S0033849423060128Savchenko V. V., Savchenko L. V., Journal of Communications Technology and Electronics, 2023, vol. 68, no. 7, pp. 757–764. https://doi.org/10.1134/S1064226923060128Savchenko A. V., Savchenko V. V., Radioelectronics and Communications Systems, 2021, vol. 64, no. 6, рр. 300–309. https://doi.org/10.3103/S0735272721060030Savchenko A. V., Savchenko V. V., Radioelectronics and Communications Systems, 2021, vol. 64, no. 6, рр. 300–309. https://doi.org/10.3103/S0735272721060030Gibson J., Information, 2019, vol. 10, no. 5, pp. 179–189. https://doi.org/10.3390/info10050179Gibson J., Information, 2019, vol. 10, no. 5, pp. 179–189. https://doi.org/10.3390/info10050179Herbst Ch. T., Elemans C. P. H., Tokuda I. T., Chatziioannou V., Švec J. G., Journal of Voice, 2023. https://doi.org/10.1016/j.jvoice.2022.10.004Herbst Ch. T., Elemans C. P. H., Tokuda I. T., Chatziioannou V., Švec J. G., Journal of Voice, 2023. https://doi.org/10.1016/j.jvoice.2022.10.004Sadok S., Leglaive S., Girin L., Alameda-Pineda X., Séguier R., Speech Communication, 2023, vol. 148, pp. 53–65. https://doi.org/10.1016/j.specom.2023.02.005Sadok S., Leglaive S., Girin L., Alameda-Pineda X., Séguier R., Speech Communication, 2023, vol. 148, pp. 53–65. https://doi.org/10.1016/j.specom.2023.02.005Савченко В. В. Дивергенция Итакуры-Саито как элемент информационной теории восприятия речи // Радиотехника и электроника. 2019. Т. 64. № 6. С. 585–592. https://doi.org/10.1134/S0033849419060093Savchenko V. V., Journal of Communications Technology and Electronics, 2019, vol. 64, no. 6, pp. 590–596. https://doi.org/10.1134/S1064226919060093Kullback S., Information Theory and Statistics, N.Y., Dover Publications, 1997, 432 p.Kullback S., Information Theory and Statistics, N.Y., Dover Publications, 1997, 432 p.Савченко В. В. Метод сравнительного тестирования параметрических оценок спектра мощности: спектральный анализ через синтез временно́го ряда // Измерительная техника. 2023. № 6. С. 56–62. https://doi.org/10.32446/0368-1025it.2023-6-56-62Savchenko V. V., Measurement Techniques, 2023, vol. 66, no. 6. https://doi.org/10.1007/s11018-023-02244-3Marple S. L. Jr., Digital spectral analysis. 2-nd ed., Dover Publications, New York, 2019, 432 р.Marple S. L. Jr., Digital spectral analysis. 2-nd ed., Dover Publications, New York, 2019, 432 р.Савченко В. В. Гибридный метод спектрального анализа речевых сигналов на основе авторегрессионной модели и периодограммы Шустера // Измерительная техника. 2023. № 3. С. 61–66. https://doi.org/10.32446/0368-1025it.2023-3-61-66Savchenko V. V., Measurement Techniques, 2023, vol. 66, no. 3, pp. 203– 210. https://doi.org/10.1007/s11018-023-02211-yОппенгейм А., Шафер Р. Цифровая обработка сигналов: Пер. с англ. 3-е изд. М.: Техносфера, 2012. 1048 с.Oppenheim A., Schafer R., Discrete-Time Signal Processing, 3d ed., Pearson, 2009, 1144 p.Kathiresan Th., Maurer D., Suter H., Dellwo V., The Journal of Acoustical Society of America, 2018, vol. 143. no. 3. pp. 1919– 1920. https://doi.org/10.1121/1.5036258Kathiresan Th., Maurer D., Suter H., Dellwo V., The Journal of Acoustical Society of America, 2018, vol. 143. no. 3. pp. 1919– 1920. https://doi.org/10.1121/1.5036258Kovela S., Valle R., Dantrey A. and Catanzaro B., IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 2023, pp. 1–5. https://doi.org/10.1109/ICASSP49357.2023.10096220Kovela S., Valle R., Dantrey A. and Catanzaro B., IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 2023, pp. 1–5. https://doi.org/10.1109/ICASSP49357.2023.10096220Sun P., Mahdi A., Xu J., Qin J., Speech Communication, 2018, vol. 101, pp. 57–69. https://doi.org/10.1016/j.specom.2018.05.006Sun P., Mahdi A., Xu J., Qin J., Speech Communication, 2018, vol. 101, pp. 57–69. https://doi.org/10.1016/j.specom.2018.05.006Tohyama M., Spectral envelope and source signature analysis, in Acoustic Signals and Hearing, Academic Press, 2020, pp. 89–110. https://doi.org/10.1016/B978-0-12-816391-7.00013-9Tohyama M., Spectral envelope and source signature analysis, in Acoustic Signals and Hearing, Academic Press, 2020, pp. 89–110. https://doi.org/10.1016/B978-0-12-816391-7.00013-9Savchenko V. V., Radioelectronics and Communications Systems, 2020, vol. 63, pp. 42–54. https://doi.org/10.3103/S0735272720010045Savchenko V. V., Radioelectronics and Communications Systems, 2020, vol. 63, pp. 42–54. https://doi.org/10.3103/S0735272720010045Eggermont J. J., Brain Responses to Auditory Mismatch and Novelty Detection, Academic Press, 2023, pp. 345–376. https://doi.org/10.1016/B978-0-443-15548-2.00011-9Eggermont J. J., Brain Responses to Auditory Mismatch and Novelty Detection, Academic Press, 2023, pp. 345–376. https://doi.org/10.1016/B978-0-443-15548-2.00011-9Oganian Yu., Bhaya-Grossman I., Johnson K., Chang E., Neuron, 2023, vol. 111, iss. 13, 2105–2118e4. https://doi.org/10.1016/j.neuron.2023.04.004Oganian Yu., Bhaya-Grossman I., Johnson K., Chang E., Neuron, 2023, vol. 111, iss. 13, 2105–2118e4. https://doi.org/10.1016/j.neuron.2023.04.004

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