informИнформатикаInformatics1816-03012617-6963UIIP NASBinform-864Research ArticleОБРАБОТКА СИГНАЛОВ, ИЗОБРАЖЕНИЙ, РЕЧИ, ТЕКСТА И РАСПОЗНАВАНИЕ ОБРАЗОВSIGNAL, IMAGE, SPEECH, TEXT PROCESSING AND PATTERN RECOGNITIONПраектаванне натуральна-моўных інтэрфейсаў для даведкавых сістэмDesign of natural-language interfaces for reference systemsГецэвічЮ. С.HetsevichYu. S.

кандыдат тэхнічных навук, загадчык лабараторыі распазнавання і сінтэзу маўлення

Cand. Sci. (Eng.), Head of the Speech Recognition and Synthesis Laboratory

yuras.hetsevich@gmail.comЖыткоУ. А.ZhitkoV. A.

кандыдат тэхнічных навук

Cand. Sci. (Eng.)

zhitko.vladimir@gmail.comГецэвічС. А.HetsevichS. A.

магістр філалагічных навук, малодшы навуковы супрацоўнік,

Master of Science, Junior Researcher

novaeimya@gmail.comКайгародаваЛ. І.KaigorodovaL. I.

магістр тэхнічных навук, аспірант, малодшы навуковы супрацоўнік,

Master of Science, Postgraduate Student, Junior Researcher

lesia.piatrouskaya@gmail.comНікалаенкаК. А.NikalaenkaK. A.

аспірант

Postgraduate Student

Anak247@gmail.comАб’яднаны інстытут праблем інфарматыкі Нацыянальнай акадэміі навук БеларусіБеларусьThe United Institute of Informatics Problems of the National Academy of Sciences of BelarusBelarusБеларускі дзяржаўны ўніверсітэт інфарматыкі і радыѐэлектронікіБеларусьBelarusian State University of Informatics and RadioelectronicsBelarus2019260820191633747Copyright © Гецэвіч Ю.С., Жытко У.А., Гецэвіч С.А., Кайгародава Л.І., Нікалаенка К.А., 20192019Гецэвіч Ю.С., Жытко У.А., Гецэвіч С.А., Кайгародава Л.І., Нікалаенка К.А.Hetsevich Y.S., Zhitko V.A., Hetsevich S.A., Kaigorodova L.I., Nikalaenka K.A.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/864

Разглядаюцца існуючыя натуральна-моўныя і маўленчыя інтэрфейсы для пытальна-адказных сістэм даведкавага прызначэння, а таксама падыходы да іх праектавання. Праводзіцца кароткі аналіз найбольш вядомых у розных сферах дзейнасці інтэлектуальных сістэм з натуральна-моўным інтэрфейсам: пры выкарыстанні ў медыцыне, тэхналогіях разумнага дому, адукацыі, прамысловасці, хуткай адаптацыі да новых тэхналогій у паўсядзѐнным жыцці. Даецца спіс асноўных існуючых сэрвісаў, якія могуць выкарыстоўвацца як персанальныя асістэнты, а таксама як аснова для пабудавання ўжо сваіх маўленчых інтэрфейсаў. Натуральна-моўныя інтэрфейсы даследуюцца з пункту гледжання выкарыстання натуральнай мовы для арганізацыі дыялогу карыстальніка з камп’ютарнай сістэмай. Пры гэтым абмяркоўваюцца асноўныя складанасці, звязаныя з неадназначнасцю натуральнай мовы і неадпаведнасцю магчымасцей рэалізацыі натуральна-моўнага інтэрфейсу спадзяванням карыстальніка. Прыводзяцца галоўныя прынцыпы мадэлявання натуральна-моўнага інтэрфейсу, які, будучы інтэлектуальнай сістэмай, у якасці асноўных сваіх кампанентаў складаецца з базы ведаў, машыны апрацоўкі ведаў і карыстальніцкага інтэрфейсу.

The description of the technology of modern natural language interfaces for intelligent systems and language interfaces for question-answering intelligent systems is presented, as well as methods and principles for their design. Analysis of the intelligent systems with natural language interfaces used in different areas are given. These areas are medicine, smart home technology, education, industry, fast adaptation to new technologies. The list of the most popular services with the natural language interfaces is presented. Each service can be used as a ready-to-use personal assistant or as a core for the development of a new customized natural language interface. The research of the natural language interfaces was conducted from the point of view of the natural language usage for the interaction between a user and the machine. The main problems here are the bias in natural language and the difficulties in the design of natural language interfaces that meet user expectations. The main principles of modeling of natural language interfaces are considered. As an intelligent system the interface consists of the database, knowledge machine and user interface. Speech recognition and speech synthesis components make natural language interfaces more convenient from the point of view of usability.

натуральна-моўны інтэрфейсгаласавы сэрвісраспазнаванне маўленнясінтэз маўленняпытальна-адказныя сістэмыnatural language interfacevoice servicesspeech recognitionspeech synthesisquestion-answering systemsReferencesAnonymous indoor navigation system on handheld mobile devices for visually impaired / C. Feng [et al.] // Intern. J. of Wireless Information Networks. − 2012. – Vol. 19, iss. 4. − P. 352−367.Feng C., Valaee S., Wain Sy Au A., Reyes S., Sorour S., …, Eizenman M. Anonymous indoor navigation system on handheld mobile devices for visually impaired. International Journal of Wireless Information Networks, 2012, vol. 19, iss. 4, pp. 352−367.Development and validation of a robust speech interface for improved human-robot interaction / A. Atrash [et al.] // Intern. J. of Social Robotics. − 2009. – No. 1. − P. 345−356.Atrash A., Kaplow R., Villemure J., West R., Yamani H., Pineau J. Development and validation of a robust speech interface for improved human-robot interaction. International Journal of Social Robotics , 2009, no. 1, pp. 345−356.Steedman, M. Combinatory categorial grammar / M. Steedman, J. Baldridge // Blackwell Sci, Oxford [Electronic resource]. – 2005. – Mode of access: ftp://ftp.cogsci.ed.ac.uk/pub/steedman/ ccg/manifesto.pdf. – Date of access: 22.10.2012.Steedman M., Baldridge J. Combinatory categorial grammar. Blackwell Sci, Oxford. Available at: ftp://ftp.cogsci.ed.ac.uk/pub/steedman/ccg/manifesto.pdf (accessed 22.10.2012).Sondik, E. The optimal control of partially observable Markov processes over a Finite Horizon / E. Sondik, R. Smallwood // Operations Research. − 1973. − Vol. 21, no. 5. − P. 1071−1088.Sondik E., Smallwood R. The optimal control of partially observable Markov processes over a Finite Horizon. Operations Research, 1973, vol. 21, no. 5, pp. 1071−1088.A powered wheelchair using a behaviour-based navigation / G. Pires [et al.] // 5th Intern. Workshop on Advanced Motion Control (AMC'98-Coimbra), Coimbra, Portugal, 29 June – 1 July 1998. – Coimbra, 1998. − P. 536−541.Pires G., Araújo R., Nunes U., Almeida A. A powered wheelchair using a behaviour-based navigation. 5th International Workshop on Advanced Motion Control (AMC'98-Coimbra), Coimbra, Portugal, 29 June – 1 July 1998. Coimbra, 1998, pp. 536−541.Complete sound and speech recognition system for health smart homes: application to the recognition of activities of daily living / M. Vacher [et al.] // New Developments in Biomedical Engineering / D. Campolo (ed.). − 2010. − P. 645−673.Vacher M., Fleury A., Portet F., Serignat J. F., Noury N. Complete sound and speech recognition system for health smart homes: application to the recognition of activities of daily living. New Developments in Biomedical Engineering. D. Campolo (ed.), 2010, pp. 645−673.Rougui, J. Audio sound event identification for distress situations and context awareness / J. Rougui, D. Istrate, W. Souidene // Proc. of the 31 Annual Intern. Conf. of the IEEE Engineering in Medicine and Biology Society (EMBC’09), Minneapolis, USA, 2−6 Sept. 2009. – Minneapolis, 2009. − P. 3501−3504.Rougui J., Istrate D., Souidene W. Audio sound event identification for distress situations and context awareness. Proceedings of the 31 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC’09), Minneapolis, USA, 2−6 September 2009. Minneapolis, 2009, pp. 3501−3504.Lines, L. Multiple voices, multiple choices: older adults’ evaluation of speech output to support independent living / L. Lines, K. S. Hone // Gerontechnology. − 2006. – Vol. 5(2). − P. 78−91.Lines L., Hone K. S. Multiple voices, multiple choices: older adults’ evaluation of speech output to support independent living. Gerontechnol, 2006, vol. 5(2), pp. 78−91.Study of a speech-based smart home system with older users / F. Godde [et al.] // Proc. of the First Intern. Workshop Intelligent User Interfaces for Ambient Assisted Living (IUI4AAL’2008), Canary Islands, Spain, 1 Jan. 2008. − Canary Islands, 2008. − P. 17–22.Godde F., Moller S., Engelbrecht K. P., Kuhnel C., Schleicher R., …, Wolters M. Study of a speech-based smart home system with older user. Proceedings of the First International Workshop Intelligent User Interfaces for Ambient Assisted Living (IUI4AAL’2008), Canary Islands, Spain, 1 January 2008. Canary Islands, 2008, pp. 17–22.Development of an automated speech recognition interface for personal emergency response systems / M. Hamill [et al.] // Journal of NeuroEngineering and Rehabilitation [Electronic resource]. − 2009. − Vol. 6, iss. 26. − Mode of access: http://www.jneuroengrehab.com/content/6/1/26. − Date of access: 15.11.2012.Hamill M., Young V., Boger J., Mihailidis A. Development of an automated speech recognition interface for personal emergency response systems. Journal of NeuroEngineering and Rehabilitation, 2009, vol. 6, iss. 26. Available at: http://www.jneuroengrehab.com/content/6/1/26 (accessed 15.11.2012).Design and evaluation of a smart home voice interface for the elderly: acceptability and objection aspects / F. Portet [et al.] // Personal and Ubiquitous Computing. – 2011. − Vol. 17, iss. 1. − P. 127−144.Portet F., Vacher M., Golanski C., Roux C., Meillon B. Design and evaluation of a smart home voice interface for the elderly: acceptability and objection aspects. Personal and Ubiquitous Computing, 2011, vol. 17, iss. 1, pp. 127−144.Huang, W. C. An intelligent multimedia e-learning system for pronunciations / W. C. Huang, T. L. Chang, H. P. Lin // Lecture Notes in Computer Science. – 2007. – Vol. 4570. − P. 84–93.Huang W. C., Chang T. L. , Lin H. P. An intelligent multimedia e-learning system for pronunciations. Lecture Notes in Computer Science, 2007, vol. 4570, pp. 84–93.Kacalak, W. Automatic recognition and verification of voice commands in natural language given by the operator of the technological device using artificial neural networks / W. Kacalak, M. Majewski // Computer Recognition Systems : Proc. of the 4th Intern. Conf. on Computer Recognition Systems (CORES ’05), Koszalin, Poland, 2005. − Koszalin, 2005. − Part V. − P. 689−696.Kacalak W., Majewski M. Automatic recognition and verification of voice commands in natural language given by the operator of the technological device using artificial neural networks. Computer Recognition Systems: Proceedings of the 4th International Conference on Computer Recognition Systems (CORES ’05), Koszalin, Poland. Koszalin, 2005, part V, pp. 689−696.Generic interaction techniques for mobile collaborative mixed systems / P. Renevier [et al.] // Computer-Aided Design of User Interfaces IV. − Holland : Kluwer Academic Publishers, 2005. − P. 309−322.Renevier P., Nigay L., Bouchet J., Pasqualetti L. Generic interaction techniques for mobile collaborative mixed systems. Computer-Aided Design of User Interfaces IV. Holland, Kluwer Academic Publishers, 2005, pp. 309−322.Aron, J. Your iPhone is listening. Siri’s ability to make sense of ordinary language sets it apart from the herd / J. Aron // New Scientist. − 2011. – No. 2836. − P. 24.Aron J. Your iPhone is listening. Siri’s ability to make sense of ordinary language sets it apart from the herd. New Scientist, 2011, no. 2836, pp 24.Google search by voice: a case study / J. Schalkwyk [et al.] // Visions of Speech: Exploring New Voice Apps in Mobile Environments, Call Centers and Clinics. − California, USA : Google, Inc. − 2010. − P. 1−35.Schalkwyk J., Beeferman D., Beaufays F., Byrne B., Chelba C., …, Strope B. Google search by voice: a case study. Visions of Speech: Exploring New Voice Apps in Mobile Environments, Call Centers and Clinics. California, USA, Google, Inc., 2010. pp. 1−35.Gales, M. J. F. Semi-tied full-covariance matrices for hidden Markov models / M. J. F. Gales // IEEE Transactions on Speech and Audio Processing. − 1997. − Vol. 7, iss. 3. − P. 272−281.Gales M. J. F. Semi-tied full-covariance matrices for hidden Markov models. IEEE Transactions on Speech and Audio Processing, 1997, vol. 7, iss. 3, pp. 272−281.Сулейманов, Д. Ш. Двухуровневый лингвистический процессор ответных текстов на естественном языке / Д. Ш. Сулейманов // Открытые семантические технологии проектирования интеллектуальных систем = Open Semantic Technologies for Intelligent Systems (OSTIS–2011): материалы I Междунар. науч.-техн. конф., Минск, 2 окт. 2011 г. / редкол. : В. В. Голенков (отв. ред.) [и др.]. – Минск : БГУИР, 2011. – С. 311–322.Sulejmanov D. Sh. Dvuhurovnevyj lingvisticheskij processor otvetnyh tekstov na estestvennom yazyke [Two-level linguistic processor for natural language answering texts]. Open Semantic Technologies for Intelligent Systems (OSTIS–2011): materialy I Mezhdunarodnoj nauchno-tehnicheskoj konferencii, Minsk, 2 oktjabrja 2011 g. [Materials of the International Scientific and Technical Conference, Minsk, 2 October 2011], Minsk, Belarusian State University of Informatics and Radioelectronics, 2011, pp. 311–322 (in Russian).Long, B. Natural language as an interface style / B. Long // Dynamic Graphics Project Department of Computer Science University of Toronto [Electronic resource]. − 1994. − Mode of access: http://www.dgp.utoronto.ca/~byron/papers/nli.html. − Date of access: 15.03.2012.Long B. Natural language as an interface style. Dynamic Graphics Project Department of Computer Science University of Toronto. Available at: http://www.dgp.toronto.edu/people/byron/papers/nli.html (accessed: 15.03.2012).Карпилович, Т. П. Алгоритмы порождения предложений естественного языка (обзор и анализ) / Т. П. Карпилович. – Минск, 1977. − 300 с.Karpilovich T. P. Algoritmy porozhdeniya predlozhenij estestvennogo yazyka (obzor i analiz). Algorithms of Natural Language Sentences Generation (Overview and Analysis). Minsk, 1977, 300 p. (in Russian).Попов, Э. В. Общение с ЭВМ на естественном языке / Э. В. Попов. – М. : Наука, 1982. − 360 с.Popov E. V. Obshchenie s EVM na estestvennom yazyke. Communication with a computer using natural Language. Moscow, Nauka, 1982, 360 p. (in Russian).

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