bsuirДоклады БГУИРDoklady BGUIR1729-76482708-0382БГУИР10.35596/1729-7648-2019-123-5-66-71bsuir-1153Research ArticleЭЛЕКТРОНИКА, РАДИОФИЗИКА, РАДИОТЕХНИКА, ИНФОРМАТИКАELECTRONICS, RADIOPHYSICS, RADIOENGINEERING, INFORMATICSСегментация речи на фонетические элементы для систем защиты речевой информацииSegmentation of speech on phonetic elements for systems of speech information protectionСейткуловЕ. Н.SeitkulovY. N.

Кандидат физико-математических наук, директор НИИ информационной безопасности криптологии

PhD, director of the institute of information security and cryptology

БоранбаевС. Н.BoranbayevS. N.

Доктор технических наук, профессор

Eurasian national university named after L.N. Gumilyov

ПотаповичА. В.PatapovichA. V.

Потапович Александр Владимирович - старший научный сотрудник НИЛ 5.3 НИЧ.

220013, Минск, ул. П. Бровки, 6, тел. +375-29-670-30-40

Patapovich Aleksandr Vladimirovich  - researcher of SRL 5.3 of R&D department.

20013, Minsk, P. Brovka st., 6, tel. +375-29-670-30-40

nil53@bsuir.edu.by.byДавыдовГ. В.DavydauH. V.

Кандидат технических наук, ведущий научный сотрудник НИЛ 5.3 НИЧ.

220013, Минск, ул. П. Бровки, 6

PhD, researcher of SRL 5.3 of R&D department.

20013, Minsk, P. Brovka st., 6

Евразийский национальный университет им. Л.Н. ГумилеваEurasian national university named after L.N. GumilyovЕвразийский национальный университет им. Л.Н. ГумилеваD.Sci, professorБелорусский государственный университет информатики и радиоэлектроникиBelarusian state university of informatics and radioelectronics201903072019056671Copyright © Сейткулов Е.Н., Боранбаев С.Н., Потапович А.В., Давыдов Г.В., 20192019Сейткулов Е.Н., Боранбаев С.Н., Потапович А.В., Давыдов Г.В.Seitkulov Y.N., Boranbayev S.N., Patapovich A.V., Davydau H.V.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/1153

Статья посвящена разработке алгоритма сегментации речи на фонетические элементы для синтеза речеподобных сигналов в системах защиты речевой информации. Основное внимание уделяется установлению границ фонетических единиц речи с учетом влияния этого фактора на качество синтезируемой речи компиляционным методом. Рассматриваются особенности установления границ фонем для слитной речи и влияние этого фактора на качество синтезируемой речи по базе фонем. Предлагается для обеспечения качественной синтезируемой речи начало и окончание фонем при сегментации устанавливать при переходе реализации сигнала через ноль, а при синтезе речеподобных сигналов использовать сплайн-функции на границах сегментов фонем.

The article is devoted to the development of speech segmentation algorithm on phonetic elements for the synthesis of speech-like signals in speech information protection systems. The main attention is paid to establishing the boundaries of phonetic units of speech, taking into account the influence of this factor on the quality of the synthesized speech by the compilation method. The features of establishing the boundaries of phonemes for fused speech and the influence of this factor on the quality of synthesized speech on the basis of phonemes are considered. It is proposed to ensure the quality of synthesized speech beginning and ending phonemes at the segmentation set in the transition implementation of a signal through zero and in the synthesis of speech-like signals to use the spline function at the boundaries of segments phonemes.

сегментация речиграницы фонемречеподобные сигналысинтезсплайн-функцииspeech segmentationphoneme boundariesspeech-like signalssynthesisspline functionsРабота выполнена при поддержке грантового финансирования КНМОН РК, №АР 05130293ReferencesSakoe H., Chiba S. Dynamic Programming Algorithm Optimization for Spoken Word Recognition // IEEE Transactions on Acoustics, Speech, and Signal Processing. 1978. Vol. ASSP-26, No. 1. P. 43-49.Sakoe H., Chiba S. Dynamic Programming Algorithm Optimization for Spoken Word Recognition // IEEE Transactions on Acoustics, Speech, and Signal Processing. 1978. Vol. ASSP-26, No. 1. P. 43-49.Scharenborg O., Wan V., Ernestus M. Unsupervised speech segmentation: An analysis of the hypothesized phone boundaries // The Journal of the Acoustical Society of America. 2010. Vol. 127, No. 2. P. 1084-1095.Scharenborg O., Wan V., Ernestus M. Unsupervised speech segmentation: An analysis of the hypothesized phone boundaries // The Journal of the Acoustical Society of America. 2010. Vol. 127, No. 2. P. 1084-1095.Gomez J.A., Calvo M. Improvements on automatic speech segmentation at the phonetic level // Materials of 16th Iberoamerican CongressProgress in Pattern Recognition, Image Analysis, Computer Vision and Applikations. 2011. P. 557-564.Gomez J.A., Calvo M. Improvements on automatic speech segmentation at the phonetic level // Materials of 16th Iberoamerican CongressProgress in Pattern Recognition, Image Analysis, Computer Vision and Applikations. 2011. P. 557-564.Bemdt D.J., Clifford J. Using Dynamic Time Warping to FindPatterns in Time Series // AAAI Proc. knowledge discovery in databases. 1994. P. 359-370.Bemdt D.J., Clifford J. Using Dynamic Time Warping to FindPatterns in Time Series // AAAI Proc. knowledge discovery in databases. 1994. P. 359-370.A Review: Automatic Speech Segmentation / Sakran A.E. [et al.] // International Jornal of Computer Science and Mobile Computing. 2017. Vol. 6, No. 4. P. 308-315.A Review: Automatic Speech Segmentation / Sakran A.E. [et al.] // International Jornal of Computer Science and Mobile Computing. 2017. Vol. 6, No. 4. P. 308-315.Makowski R., Hossa R. Automatic speech signal segmentation based on the innovation adaptive filter // International Journal of Applied Mathematics and Computer Science. 2014. Vol. 24, No. 2. P. 259-270.Makowski R., Hossa R. Automatic speech signal segmentation based on the innovation adaptive filter // International Journal of Applied Mathematics and Computer Science. 2014. Vol. 24, No. 2. P. 259-270.Kamarauskas J. Automatic Segmetation of Phonemes using Artificial Neural Networks // Elektronika ir Elektrotechnika. 2006. Vol. 72, No. 8. P. 39-42.Kamarauskas J. Automatic Segmetation of Phonemes using Artificial Neural Networks // Elektronika ir Elektrotechnika. 2006. Vol. 72, No. 8. P. 39-42.Automatic Silence/Unvoiced/Voiced Classification of Bangla Velar Phonemes: New Approach / Syed Akhter Hossain [et al.] // 8th ICCIT. Dhaka, 2005.Automatic Silence/Unvoiced/Voiced Classification of Bangla Velar Phonemes: New Approach / Syed Akhter Hossain [et al.] // 8th ICCIT. Dhaka, 2005.. Highly accurate phonetic segmentation using boundary correction models and system fusion / A. Stolcke [et al.] // 2014 IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP). IEEE, 2014. P. 5552-5556.. Highly accurate phonetic segmentation using boundary correction models and system fusion / A. Stolcke [et al.] // 2014 IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP). IEEE, 2014. P. 5552-5556.Method for protecting speech information / H.V. Davydau [et al.] // Doklady BGUIR. 2015. N° 8 (94). P. 107-110.Method for protecting speech information / H.V. Davydau [et al.] // Doklady BGUIR. 2015. N° 8 (94). P. 107-110.Rationale for the method of formation of the combined speech masking signals / Y. Seitkulov [et al.] // IEEE 8th International Conference on Application on Information and Communication Technologies (AICT). Astana, Kazakhstan, 2014.Rationale for the method of formation of the combined speech masking signals / Y. Seitkulov [et al.] // IEEE 8th International Conference on Application on Information and Communication Technologies (AICT). Astana, Kazakhstan, 2014.Sorokin V.N. Segmentation of the period of the fundamental tone of a voice source // Acoustical Physics. 2016. Vol. 62, No. 2. P. 244-254.Sorokin V.N. Segmentation of the period of the fundamental tone of a voice source // Acoustical Physics. 2016. Vol. 62, No. 2. P. 244-254.Algoritym of forming speech base units using the method of dynamic programming / Seitkulov Y.N. [et al.] // Journal of Theoretical and Applied Information Technology. 2018. Vol. 96, No 23. P. 7928-7941.Algoritym of forming speech base units using the method of dynamic programming / Seitkulov Y.N. [et al.] // Journal of Theoretical and Applied Information Technology. 2018. Vol. 96, No 23. P. 7928-7941.

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