Article 11313

Title of the article

                                       SPEECH RECOGNITION BY MEANS OF HIDDEN MARKOV MODELS                                        IN ASSOCIATIVE OSCILLOMETRIC MEDIUM


Ognev Ivan Vasil'evich, Doctor of engineering sciences, professor, sub-department of computing technology, National Research University "Moscow Power Engineering University" (14 Krasnokazarmennaya street, Moscow, Russia),
Paramonov Pavel Aleksandrovich, Postgraduate student, National Research University "Moscow Power Engineering University" (14 Krasnokazarmennaya street, Moscow, Russia), 

Index UDK



Background. Application of hidden Markov models is based on recursive procedures featuring computational complexity. Herewith, the systems of automatic speech recognition are often required to function in real time mode, and therefore the increase of operation speed thereof is a topical problem.
Мaterials and methods. One of the approaches to solve the said problem is the realization of hardware support of computing in associative oscillometric medium. The said approach is characterized by low hardware expenditures due to the simplicity of basic cellular assemblies and functions performed thereof, as well as by high operation speed independent of the length of the sequence under analysis and of the number of conditions of hidden Markov models, due to concurrency and conveyor nature of computing.
Results. The authors suggest hardware implementation to compute the probability function of direct distribution in the medium. The researchers built a program model via Mathlab package in order to experimentally evaluate the precision of computing results in associative oscillometric medium by the example of Russian words recognition.
Conclusions. The obtained precision value of the results by the example of Russian words recognition demonstrates the efficiency of the applied model. 

Key words

associative media, speech recognition, hidden markov models.

Download PDF

1. Becchetti C., Ricotti L. P. Speech Recognition. Theory and C++ Implementation. Wiley, 1999, 428 p.
2. Huang X., Acero A. Spoken language processing: a guide to theory, algorithm, and system de-velopment. Prentice Hall, 2001, 1008 p.
3. Mosleh M., Setayeshi S., Mehdi Lotfinejad M., Mirshekari A. The 2nd International Conference on Computer and Automation Engineering (ICCAE). 2010, vol. 3, pp. 75–78.
4. Ognev I. V., Paramonov P. A. Informatsionnye sredstva i tekhnologii: tr. XX Mezhdunar. nauch.-tekhn. konf. [Information devices and technology: Proceedings of XXth International scientific technical conference]. Moscow: MEI, 2012, pp. 53–58.
5. Ognev I. V., Ognev A. I., Paramonov P. A., Sutula N. A. Pattern Recognition and Image Analysis: New Information Technologies: the 11th International Conference. 2013, vol. 1, pp. 114–117.
6. Rabiner L., Juang B.-H. Fundamentals of speech recognition. Prentice Hall, 1993, 507 p.
7. Rabiner L. Trudy instituta inzhenerov po elektrotekhnike i radioelektronike [Proceedings of the Institute of electrical engineering and radio electronics]. Moscow: Mir, 1989, vol. 77, no. 2, pp. 86–120.
8. Komarov A. N. Issledovanie i razrabotka assotsiativnykh sred i metodov obrabotki informatsii: dis. kand. tekhn. nauk [Research and development of associative media and methods of data processing: dissertation to apply for the degree of the candidate of engineering sciences]. Moscow: MEI(TU), 2002, 194 p.
9. Komarov A. N., Ognev I. V., Podolin P. B. Vychislitel'nye sistemy i tekhnologii obrabotki informatsii: mezhvuz. sb. nauchn. tr. Vyp. 5 (30) [Computing systems and technologies of data processing: interuniversity collected papers. Issue 5 (30)]. Penza: Inf.-izd. tsentr PGU, 2006, 200 p.
10. Ognev I. V., Podolin P. B. Izvestiya vysshikh uchebnykh zavedeniy. Povolzhskiy region. Tekhnicheskie nauki. [University proceedings. Volga region. Engineering sciences]. 2006, no. 6, pp. 55–67.


Дата создания: 28.08.2014 14:02
Дата обновления: 29.08.2014 10:24