he paper presents automatic speaker recognition system, implemented in the Matlab environment, and demonstrates how to achieve and optimize various elements of the system. The main emphasis was put on features selection of speech signal using a genetic algorithm, which takes into account synergy of features. The results of the selected elements of optimizing classifier have been also shown, including the number of Gaussian distributions used to model each of the voices. In addition during creating voice models, the universal voice model have been used.
2) Garofolo J. S. et al., TIMIT Acoustic-Phonetic Continuous Speech Corpus LDC93S1, Linguistic Data Consortium, Philadelphia, 1993.
3) Martin A., Przybocki M., 2002 NIST Speaker Recognition Evaluation LDC2004S04, Linguistic Data Consortium, Philadelphia, 2004.
4) Brookes M., VOICEBOX: Speech Processing Toolbox for MATLAB, http://www.ee.ic.ac.uk/np/staff/dmb/voicebox/voicebox.html, 2002.
5) Kamiński K., Majda E., Dobrowolski A. P., Automatic speaker recognition using Gaussian Mixture Models, 17th IEEE SPA Conference, 2013, s. 220-225.
6) Dobrowolski A. P., Majda E., Cepstral analysis in the speakers recognition systems, 15th IEEE SPA Conference, 2011, s. 85-90.
7) Ludwig O., Nunes U., Novel Maximum-Margin Training Algorithms for Supervised Neural Networks, IEEE Transactions on Neural Networks, tom 21, nr 6, s. 972-984, 2010.
8) Reynolds, D. A., Quatieri, T. F., Dunn, R. B., Speaker Verification Using Adapted Gaussian Mixture Models, Digital Signal Processing, nr 10, s. 19-41, 2000.
9) Goldberg D. E., Algorytmy genetyczne i ich zastosowanie, WNT, Warszawa, 2003
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.