informИнформатикаInformatics1816-03012617-6963UIIP NASBinform-748Research ArticleОБРАБОТКА СИГНАЛОВ, ИЗОБРАЖЕНИЙ, РЕЧИ, ТЕКСТА И РАСПОЗНАВАНИЕ ОБРАЗОВSIGNAL, IMAGE, SPEECH, TEXT PROCESSING AND PATTERN RECOGNITIONФанетычная мінімізацыя корпуса тэкстаў на беларускай мове для навучання сістэмы сінтэзу маўленняPhonetic minimization of the text corpus in Belarusian for the speech synthesis system trainingЛысыС. I.LysyS. I.

малодшы навуковы супрацоўнік

Junior Researcher

stanislau.lysy@gmail.comАб’яднаны інстытут праблем інфарматыкі Нацыянальнай акадэміі навук Беларусі, МінскThe United Institute of Informatics Problems of the National Academyof Sciences of Belarus, Minsk2019210120191617585Copyright © Лысы С.I., 20192019Лысы С.I.Lysy S.I.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://inf.grid.by/jour/article/view/748

Большасць сучасных сістэм сінтэзу маўлення базіруюць сваю працу на корпусным метадзе. Корпусны метад, у адрозненні ад папулярнага раней кампіляцыйнага, выкарыстоўвае базу дадзеных натуральнага маўлення, якая складаецца не з асобных спецыяльна выбраных элементаў кампіляцыі, а ўяўляе сабой корпус фанаграм натуральнага маўлення. Для дасягнення высокай якасці сінтэзаванага маўлення пры такім падыходзе патрабуюцца вялікія аб’ѐмы тэкставай і адпаведнай гукавой інфармацыі, што з’яўляецца істотнай праблемай для так званых нерэсурсных моў, да якіх адносіцца і беларуская. У такім выпадку, як правіла, прымяняецца фанетычная мінімізацыя – адмысловы адбор тэкстаў, у выніку якога аб’ѐм тэкставага корпуса максімальна змяншаецца, але пры гэтым захоўваецца фанетычная паўната. У артыкуле разглядаюцца звесткі пра сутнасць і спосаб працы корпуснага метаду генерацыі гукавога сігналу ў сістэмах сінтэзу маўлення, прыводзіцца падрабязны агляд падыходаў да фарміравання тэкставых і маўленчых карпусоў, неабходных для генерацыі маўлення корпусным метадам. Другая палова працы прысвечана апісанню распрацаванага алгарытму фанетычнай мінімізацыі корпуса тэкстаў на беларускай мове, а таксама тэхнічных і лінгвістычных рэсурсаў, выкарыстаных для яго рэалізацыі. Прыводзяцца апісанні распрацаванага праграмнага прататыпа і шэрагу праведзеных аўтарам эксперыментаў па фанетычнай мінімізацыі.

The most modern speech synthesis systems are based on the corpus-based method. The corpus-based method, unlike previously popular compilation method, uses natural speech database that does not consist of separate specially selected elements of compilation, but represents the corpus of phonograms of natural speech. Large amounts of text and corresponding audio information, which represents a significant challenge for so-called under-resourced languages, which include Belarusian, are required to achieve high-quality synthesized speech in this approach. In this case, a common approach is to use phonetic minimization, special selection of texts, when the amount of text corpus is maximally reduced, but at the same time phonetic fullness is preserved. The article discusses the information about the nature and the functioning the corpus-based method of sound signal generation in speech synthesis systems, provides a detailed overview of the approaches to the formation of text and speech corpuses, required for speech generation by the corpus-based method. The second half of the work is devoted to the description of the elaborated algorithm of the text corpus phonetic minimization in Belarusian language, as well as technical and linguistic resources used to implement it. A description of the developed software prototype as well as a description of the series of experiments on phonetic minimization are given to demonstrate the efficiency of the algorithm.

фанетычная мінімізацыябеларуская мовасінтэз маўленнякорпусны метадкорпус тэкстаўphonetic minimizationthe Belarusian languagespeech synthesiscorpus-based methodtext corpusДаследаванне выканана пры падтрымцы гранта НАН Беларусі № 2018-25-032 «Алгарытмы інтэрнэт-сінтэзатара беларускага маўлення і аўтаматызаванага стварэння лінгвістычных рэсурсаў», а таксама ў межах праекта БРФФД № Ф17МС-039 «Высакаякасны інтэрнэт-увод і інтэрнэт-вывад маўлення, захаванне і сістэматызацыя вялікіх аб’ѐмаў (Big Data) маўлення».ReferencesSafarik, R. Unified approach to development of ASR systems for east slavic languages / R. Safarik,Safarik R., Nouza J., ed. Camelin N., Estève Y., Martín-Vide C. Unified approach to development of ASR systems for east slavic languages. Proceedings of 5th International Conference "Statistical Language and Speech Processing" (SLSP’2017), Le Mans, France, 23–25 October 2017. Springer, 2017, pp. 193–203.J. Nouza; ed. N. Camelin, Y. Estève, C. Martín-Vide // Proc. of 5th Intern. Conf. «Statistical Language and Speech Processing» (SLSP’2017), Le Mans, France, 23–25 Oct. 2017. – Springer, 2017. – P. 193–203.Hetsevich Yu. S. Aŭtamatyzavanaja apracoŭka simvaĺnych vyrazaŭ u tekstach dlia sistemy sintezu bielaruskaha maŭliennia [Automated processing symbol expressions in the texts for belarusian speech-to-text synthesis]. Informatika [Informatics], 2011, no. 4(32), pp. 82–93 (in Belarusian).Гецэвіч, Ю. С. Аўтаматызаваная апрацоўка сімвальных выразаў у тэкстах для сістэмы сінтэзу беларускага маўлення / Ю. С. Гецэвіч // Информатика. – 2011. – № 4(32). – С. 82–93.Lysy S. I., Hetsevich Yu. S. Hienieracyja nacyjanaĺnaj transkrypcyi tekstaŭ na bielaruskaj movie [Generating the national transcription of texts in Belarusian]. Informatika [Informatics], 2017, no. 2(54), pp. 84–92 (in Belarusian).Лысы, С. І. Генерацыя нацыянальнай транскрыпцыі тэкстаў на беларускай мове / С. І. Лысы, Ю. С. Гецэвіч // Информатика. – 2017. – № 2(54). – C. 84–92.Hunt A., Black A. Unit selection in a concatenative speech synthesis system using a large speech database. Proceedings of IEEE International Conference "Acoustic, Speech and Signal Processing" (ICASSP’96), Atlanta, USA, 7–10 May 1996. Atlanta, 1996, vol. 1, pp. 373–376.Hunt, A. Unit selection in a concatenative speech synthesis system using a large speech database / A. Hunt, A. Black // Proc. of IEEE Intern. Conf. «Acoustic, Speech and Signal Processing» (ICASSP’96), Atlanta, USA, 7–10 May 1996. – Atlanta, 1996. – Vol. 1. – P. 373–376.Lobanov B. M., Cirul'nik L. I. Komp'yuternyj sintez i klonirovanie rechi. Computer Synthesis and Speech Cloning. Minsk, Belаruskaya navuka, 2008, 344 p. (in Russian).Лобанов, Б. М. Компьютерный синтез и клонирование речи / Б. М. Лобанов, Л. И. Цирульник // Минск : Беларус. навука, 2008. – 344 с.Coorman G., Fackrell J., Rutten P., Van Coile B. Segment selection in the L&H Realspeak laboratory TTS system. Proceedings of 6th International Conference "Spoken Language Processing" (ICSLP’2000), Beijing, China, 16–20 October 2000. Beijing, 2000, vol. 2, pp. 395–398.Segment selection in the L&H Realspeak laboratory TTS system / G. Coorman [et. al.] // Proc. of 6th Intern. Conf. «Spoken Language Processing» (ICSLP’2000), Beijing, China, 16–20 Oct. 2000. – Beijing, 2000. – Vol. 2. – P. 395–398.Godfrey J., Zampolli A. Language Resources. Survey of the State of the Art in Human Language Technology. Cambrige University Press, 1996, ch. 12, pp. 357–384.Godfrey, J. Language Resources / J. Godfrey, A. Zampolli // Survey of the State of the Art in Human Language Technology. – Cambrige University Press, 1996. – Ch. 12. – P. 357–384.Zinovieva N. Phonetically sufficient allophonic database for concatenation synthesis of russian speech. Proceedings of the 13th Section "International Congress of Phonetic Sciences" (ICPhS’95), Stockholm, Sweden, 13–19 August 1995. Stockholm, 1995, vol. 2, pp. 358–361.Zinovieva, N. Phonetically sufficient allophonic database for concatenation synthesis of russian speech / N. Zinovieva // Proc. of the 13th Section «Intern. Congress of Phonetic Sciences» (ICPhS’95), Stockholm, Sweden, 13–19 Aug. 1995. – Stockholm, 1995. – Vol. 2. – P. 358–361.Fotinea S.-E., Tambouratzis G., Carayannis G. Constructing a segment database for greek time domainFotinea, S.-E. Constructing a segment database for greek time domain speech synthesis / S.-E. Fotinea, G. Tambouratzis, G. Carayannis // Proc. of 7th European Conf. «Speech Communication and Technology» (EUROSPEECH’2001), Aalborg, Denmark, 3–7 Sept. 2001. – Aalborg, 2001. – Vol. 3. – P. 2075–2078.speech synthesis. Proceedings of 7th European Conference "Speech Communication and Technology" (EUROSPEECH’2001), Aalborg, Denmark, 3–7 September 2001. Aalborg, 2001, vol. 3, pp. 2075–2078.Lambert, T. A database design for a TTS synthesis system using lexical diphones / T. Lambert, A. Breen // Proc. of 9th European Conf. «Speech Communication and Technology» (InterSpeech’2004), Jeju Island, Korea, 4–8 Oct. 2004. – Jeju Island, 2004. – P. 1381–1384.Lambert T., Breen A. A database design for a TTS synthesis system using lexical diphones. Proceedings of 9th European Conference "Speech Communication and Technology" (InterSpeech’2004), Jeju Island, Korea, 4–8 October 2004. Jeju Island, 2004, pp. 1381–1384.Lyudovyk, T. Speech databases used for concatenative speech synthesis / T. Lyudovyk, M. Sazhok // Proc. of 7th All-Ukrainian Intern. Conf. on Signal/Image Processing and Pattern Recognition (UkrObraz’2004). – Kyjiv, 2004. – P. 111–114.Lyudovyk T., Sazhok M. Speech databases used for concatenative speech synthesis. Proceedings of 7th All-Ukrainian International Conference on Signal/Image Processing and Pattern Recognition (UkrObraz’2004). Kyjiv, 2004, pp. 111–114.Закревский, А. Д. Основы логического проектирования / А. Д. Закревский, Ю. В. Поттосин, Л. Д. Черемисинова. – Минск : ОИПИ НАН Беларуси, 2004. – Кн. 1. Комбинаторные алгоритмы дискретной математики. – 226 с.Zakrevskij A. D., Pottosin Yu. V., Cheremisinova L. D. Osnovy logicheskogo proektirovaniya [Basics of logical design]. Kniga 1. Kombinatornye algoritmy diskretnoj matematiki [Book 1. Combinatorial algorithms of discrete mathematics]. Minsk, the United Institute of Informatics Problems National Academy of Sciences of Belarus, 2004, 226 p. (in Russian).Introduction to Algorithms / T. H. Cormen [et. al.]. – 3rd ed. – Cambridge : The MIT Press, 2009. – 1292 p.Cormen T. H., Leiserson Ch. E., Rivest R. L., Stein C. Introduction to Algorithms. 3d Ed. Cambridge, The MIT Press, 2009, 1292 p.Hue, X. Genetic algorithms for optimization / X. Hue. – Edinburgh : Edinburgh Parallel Computing Centre Press, 1997. – 276 p.Hue X. Genetic Algorithms for Optimization. Edinburgh, Edinburgh Parallel Computing Centre Press, 1997, 276 p.Matoušek, J. ARTIC: A new Czech text-to-speech system using statistical approach to speech segment database construction / J. Matoušek, J. Psutka // Proc. of the 6th Intern. Conf. on Spoken Language Processing (ICSLP’2000), Beijing, China, 16–20 Oct. 2000. – Beijing, 2000. – Vol. 4. – P. 612–615.Matoušek J., Psutka J. ARTIC: A new Czech text-to-speech system using statistical approach to speech segment database construction. Proceedings of the 6th International Conference on Spoken Language Processing (ICSLP’2000), Beijing, China, 16–20 October 2000. Beijing, 2000, vol. 4, pp. 612–615.Barbot, N. Comparing performance of different set-covering strategies for linguistic content optimization in speech corpora / N. Barbot, O. Boeffard, A. Delhay // Proc. of the Intern. Conf. on Language Resources and Evaluation (LREC’12). – Istanbul, 2012. – P. 969–974.Barbot N., Boëffard O., Delhay A. Comparing performance of different set-covering strategies for linguistic content optimization in speech corpora. Proceedings of the International Conference on Language Resources and Evaluation (LREC’12). Istanbul, 2012, pp. 969–974.Development of syllable-based text to speech synthesis system in Bengali / N. P. Narendra [et. al.]. // Intern. J. of Speech Technology. – 2011. – No. 14(3). – P. 167–181.Narendra N. P., Rao K. S.,•Ghosh K.,•Vempada R. R.,•Maity S. Development of syllable-based text to speech synthesis system in Bengali. International Journal of Speech Technology, 2011, no 14(3), pp. 167–181.Kayte, S. A review of unit selection speech synthesis / S. Kayte, M. Mundada, C. Kayte // Intern. J. of Advanced Research in Computer Science and Software Engineering. – 2015. – No. 5(10). – P. 475–479.Kayte S., Mundada M., Kayte C. A review of unit selection speech synthesis. International Journal of Advanced Research in Computer Science and Software Engineering, 2015, no 5(10), pp. 475–479.Corpus and voices for catalan speech synthesis / A. Bonafonte [et. al.] // Proc. of the Intern. Conf. on Language Resources and Evaluation (LREC’2008), Marrakech, Morocco, 26 May–1 June 2008. – Marrakech, 2008. – P. 3325–3329.Bonafonte A., Adell J., Esquerra I., Gallego S., Moreno A., Pérez J. Corpus and voices for catalan speech synthesis. Proceedings of the International Conference on Language Resources and Evaluation (LREC’2008), Marrakech, Morocco, 26 May–1 June 2008. Marrakech, 2008, pp. 3325–3329.Casademont, E. G. Building synthetic voices in the META-NET framework / E. G. Casademont, A. Bonafonte, M. Moreno // Proc. of the 8th Intern. Conf. on Language Resources and Evaluation (LREC’12), Istanbul, Turkey, 21–27 May 2012. – Istanbul, 2012. – P. 3322–3326.Casademont E. G., Bonafonte A., Moreno M. Building synthetic voices in the META-NET framework. Proceedings of the 8th International Conference on Language Resources and Evaluation (LREC’12), Istanbul, Turkey, 21–27 May 2012. Istanbul, 2012, pp. 3322–3326.

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