Vol. 6 (05) pp. 703-709 DOI: 10.21474/IJAR01/7086

SPEECH RECOGNITION USING THE EMPIRICAL MODE DECOMPOSITION METHOD.

  • Computer Science Dept., Institute of Space and Information Technology, Siberian Federal University, Kirenskogo, 26, Krasnoyarsk, 660074, Russia.
15 Downloads 89 Views
Crossref

Download Full Paper (PDF)

Abstract

In this paper the using of empirical mode decomposition for creation of the Russian phoneme models in a system of speech-to-text conversion is considered. The proposed method is compared with the Fourier transform and wavelet transform. The experimental evaluation has shown that this method has advantages in the task of speech features formation (within neural network approach).

Keywords

Article Analytics

References

  1. Davydov, A.V., 2005, Digital signal processing: thematic lections, Yekaterinburg: UGGU, Collection of Digital Documents.
  2. Dremin,?I.M., Ivanov, O.V., Nechitaylo, V.A. 2001, Wavelets and using of them, Advances in Physical Sciences, 171, 5, 465-500.
  3. Medvedev,?M.S., 2006, Using the wavelet transform in russian phoneme model construction, Bulletin of Krasnoyarsk State University, 193-201.
  4. Qin, S.R., Zhong, Y.M., 2006, A new envelope algorithm of Hilbert?Huang Transform, Mechanical Systems and Signal Processing, 20, 1941?1952.
  5. E., Huang, Samuel, S.P., Shen, 2014, The Hilbert-Huang transform and its applications, World Scientific Publishing Co. Pte. Ltd., 5 Toh Tuck. Link: Singapore.

How to Cite This Article

M. S. Medvedev. (2018); SPEECH RECOGNITION USING THE EMPIRICAL MODE DECOMPOSITION METHOD., Int. J. of Adv. Res., 6 (05), 703-709, ISSN 2320-5407. DOI: https://doi.org/10.21474/IJAR01/7086

Corresponding Author

Medvedev Maxim
Siberian federal University
Creative Commons Attribution 4.0 This work is licensed under a Creative Commons Attribution 4.0 International License.