Voice recognition through the use of Gabor transform and heuristic algorithm

• Autorzy: Woźniak M. , Połap D.

Identyfikatory

DOI

10.1515/eletel-2017-0021

• Języki publikacji: EN

Abstrakty

EN

Increasingly popular use of verification methods based on specific characteristics of people like eyeball, fingerprint or voice makes inventing more accurate and irrefutable methods of that urgent. In this work we present voice verification based on Gabor transformation. Proposed approach involves creation of spectrogram, which serves as a habitat for the population in selected heuristic algorithm. The use of heuristic allows for feature extraction to enable identity verification using classical neural network. The results of the research are presented and discussed to show efficiency of the proposed methodology.

Słowa kluczowe

EN

neural networks; voice recognition; Gabor transform; heuristic algorithm; swarm

• Wydawca: Polish Academy of Sciences, Committee of Electronics and Telecommunication
• Czasopismo: International Journal of Electronics and Telecommunications
• Rocznik: 2017
• Tom: Vol. 63, No. 2
• Strony: 159--164
• Opis fizyczny: Bibliogr. 12 poz., wykr.

Twórcy

autor

Woźniak M.

• Institute of Mathematics, Silesian University of Technology, Poland

autor

Połap D.

• Institute of Mathematics, Silesian University of Technology, Poland

Bibliografia

• [1] R. Grycuk, M. Gabryel, M. Scherer, and S. Voloshynovskiy, “Image descriptor based on edge detection and crawler algorithm,” in International Conference on Artificial Intelligence and Soft Computing. Springer, 2016, pp. 647–659.
• [2] R. Grycuk, M. Gabryel, R. Nowicki, and R. Scherer, “Content-based image retrieval optimization by differential evolution,” in Evolutionary Computation (CEC), 2016 IEEE Congress on. IEEE, 2016, pp. 86–93.
• [3] J. Kim, K. Oh, A. B.-J. Teoh, and K.-A. Toh, “Finger-knuckle-print for identity verification based on difference images,” in Industrial Electronics and Applications (ICIEA), 2016 IEEE 11th Conference on. IEEE, 2016, pp. 1073–1077.
• [4] K. Cpałka, M. Zalasiński, and L. Rutkowski, “A new algorithm for identity verification based on the analysis of a handwritten dynamic signature,” Applied soft computing, vol. 43, pp. 47–56, 2016.
• [5] S. N. Awan, N. Roy, D. Zhang, and S. M. Cohen, “Validation of the cepstral spectral index of dysphonia (csid) as a screening tool for voice disorders: development of clinical cutoff scores,” Journal of Voice, vol. 30, no. 2, pp. 130–144, 2016.
• [6] M. Pal and G. Saha, “On robustness of speech based biometric systems against voice conversion attack,” Applied Soft Computing, vol. 30, pp. 214–228, 2015.
• [7] M. Usha, Y. Geetha, and Y. Darshan, “Objective identification of prepubertal female singers and non-singers by singing power ratio using matlab,” Journal of Voice, 2016.
• [8] E. Krasnova, E. Bulgakova, and V. Shchemelinin, “Performance evaluation of acoustic-spectrographic voice identification method in native and non-native speech,” Performance Evaluation, vol. 5656, p. 10004820, 2016.
• [9] S. Mirjalili, “Dragonfly algorithm: a new meta-heuristic optimization technique for solving single-objective, discrete, and multi-objective problems,” Neural Computing and Applications, vol. 27, no. 4, pp. 1053–1073, 2016.
• [10] P. Werbos, “Beyond regression: New tools for prediction and analysis in the behavioral sciences,” 1974.
• [11] K. Gregor, I. Danihelka, A. Graves, D. J. Rezende, and D. Wierstra, “Draw: A recurrent neural network for image generation,” arXiv preprint arXiv:1502.04623, 2015.
• [12] D. Williams and G. Hinton, “Learning representations by backpropagating errors,” Nature, vol. 323, pp. 533–536, 1986.

Uwagi

PL

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę (zadania 2017).