Prospects for implementing embedded automatic speech recognition systems based on the RISC microcontrollers

Authors

DOI:

https://doi.org/10.20535/SRIT.2308-8893.2016.4.06

Keywords:

automatic speach recognition, embedded systems, microcontrollers systems

Abstract

The implementation of automatic speech recognition systems as a part of the sound interface of intelligent information management systems promotes an increase in the efficiency of human interaction with these systems. Lately, the research in the field of embedded automatic recognition systems is especially of a high interest. This article analyzes the prospects of the implementation of embedded automatic speech recognition systems based on high-performance RISC microcontrollers. The advantages have been substantiated of such an implementation in comparison with other solutions in this area. The characteristics of high performance microcontroller families have been compared. The possibility of implementing each stage of recognition tasks using microcontroller systems has been explored.

Author Biography

Igor Andreevich Martynyuk, The department of information technologies and mathematical disciplines of European university, Kyiv, Ukraine.

Igor Andreevich Martynyuk,

a graduate student of the department of information technologies and mathematical disciplines of European university, Kyiv, Ukraine.

Scientific interests: automatic speech recognition.

References

Martynjuk I.A. Aktual'nist' ta osnovni problemy realizatsiyi tekhnolohij avtomatychnoho rozpiznavannja movy dlja vbudovanykh system / I.A. Martynjuk, V.A. Lakhno // Informatsijna bezpeka ta komp’juterni tekhnolohiyi: zb. tez dop. mizhnar. nauk.-prakt. konf., 24–25 berez. 2016 r. — Kirovohrad: KNTU, 2016. — S. 112–113.

Compact hardware liquid state machines on FPGA for real-time speech recognition [Text] / [B. Schrauwen, M. D’Haene, D. Verstraeten et al.] // Neural Networks. — 2008. — 21, № 2–3. — P. 511–523.

Speech recognition on an FPGA using discrete and continuous Hidden Markov Models [Text] / S.J. Melnikoff, S.F. Quigley, M.J. Russell // Lecture Notes in Computer Science. — 2002. — № 2438. — P. 202–211.

Pan Shing-Tai. The implementation of speech recognition systems on FPGA-based embedded systems with SOC architecture [Text] / Shing-Tai Pan, Chih-Chin Lai, Bo-Yu Tsai // International journal of innovative computing, information and control. — 2011. — 7, № 11. — P. 6161–6175.

Hu X. Isolated word speech recognition system based on FPGA [Text] / X. Hu, H. Zhang, L. Zhan et al // Journ. of Computers. — 2013. — 8, № 12. — P. 3216–3222.

Li J. Embedded speaker recognition system design and implementation based on FPGA [Text] / J. Li, D. An, L. Lang et al. // Procedia Engineering. — 2012. — 29. — P. 2633–2637.

Aldahoud A. Robust automatic speech recognition system implemented in a hybrid design DSP-FPGA [Text] / A. Aldahoud, H. Atoui, M. Fezari // International Journal of signal processing, image processing and pattern recognition. — 2013. — 6, № 5. — P. 333–342.

Bourke P.J. A Low-Power Hardware Architecture for Speech Recognition Search : thesis submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy / P.J. Bourke. – Pittsburgh, PA : Carnegie Mellon University, 2011. — 166 p.

Wei Z. Embedded system for speech recognition and image processing [Text] / Z. Wei, J. Liang // Journal of electrical and electronic engineering. — 2015. — 2, № 6. — P. 89–93.

Varshney N. Embedded speech recognition system [Text] / N. Varshney, S. Singh // International journal of advanced research in electrical, electronics and instrumentation energy. — 2014. — 3, № 4. — P. 9218–9227.

Moving Speech Recognition from Software to Silicon: the In Silico VoxProject : research report (final) : 888.012 / C.L. Edward, K. Yu, R.A. Rutenbar, C. Tsuhan. — Pittsburgh: Carnegie Mellon University, 2006. — 4 p.

Suryawanshi U.J. Hardware implementation of speech recognition using mfcc and euclidean distance [Text] / U.J. Suryawanshi, prof. dr. S.R. Ganorkar // International journal of advanced research in electrical, electronics and instrumentation engineering. — 2014. — 3, № 8. — P. 11248–11254.

Lippman R.P. An introduction to computing with neural nets [Text] / R.P. Lippman // IEEE Acoustics, speech and signal processing magazine. — 1987. — 4, № 2 — P. 4–22.

Cortex-M Series [Electronic resource]. — Access mode: http://www.arm.com/ products/ processors/cortex-m/

STMicroelectronics STM32F7 Series [Electronic resource]. — Access mode: http://www.st.com/web/en/catalog/mmc/FM141/SC1169/SS1858/

NXP Kinetis V Series [Electronic resource]. — Access mode: http://www.nxp.com/ products/microcontrollers-and-processors/arm-processors/kinetis-cortex-m-mcus/ v-series

Atmel SAM V Series [Electronic resource]. — Access mode: http://www.atmel. com/ru/ru/products/microcontrollers/arm/sam-v-mcus.aspx

Presnjakov I.N. Avtomaticheskoe raspoznavanie rechi v kanalah peredachi [Tekst] / I.N. Presnjakov, A.V. Omel'chenko, S.V. Omel'chenko // Radioelektronika i informatika. — 2002. — № 1. — S. 26–31.

Zubakov A.P. Fur'e i vejvlet-preobrazovanija v probleme raspoznavanija rechi [Tekst] / A.P. Zubakov // Vestn. Tamb. un-ta. Serija: Estestvennye i tehnicheskie nauki. — 2010. — 15, № 6. — S. 1893–1899.

Mescherjakov R.V. Struktura sistem sinteza i raspoznavanija rechi / R.V. Mescherjakov // Izvestija Tomsk. politehn. un-ta. — 2009. — № 5. — S. 121–126.

Rabiner L.R. A tutorial on hidden Markov models and selected applications in speech recognition [Text] / L.R. Rabiner // Proceedings of the IEEE. — 1989. — 77, № 2. — P. 257–286.

Alimuradov A.K. Obzor i klassifikatsija metodov obrabotki rechevyh signalov v sistemah raspoznavanija rechi [Tekst] / A.K. Alimuradov, P.P. Churakov // Izmerenie. Monitoring. Upravlenie. Kontrol'. — 2015. — № 2. — S. 27–35.

Published

2016-12-15

Issue

Section

Progressive information technologies, high-efficiency computer systems