Automatic determination of a speaker’s gender based on the Cauchy distribution in the octave frequency band
Keywords:Cauchy distribution, formant frequencies, antiformant frequencies, moment functions, gender recognition
Algorithms for recognition of a speaker’s gender based on the use of the Cauchy distribution in the octave frequency band with a geometric mean frequency of 125 Hz are obtained. Classifiers based on the maximum logarithm of the likelihood function are constructed. The algorithm for determining the speaker’s gender is considered, where not only the logarithm of the Cauchy distribution in the octave frequency band is taken into account, but also estimates of the average value of the formant frequencies and the antiformant frequencies. Studies of the probability of correct recognition of the speaker's gender determination algorithms are carried out
Kalyuzhnyiy, A. Ya., Semenov, V. Yu. (2009). Metod identifikatsii pola diktora na osnove modelirovaniya akusticheskih parametrov golosa gaussovyimi smesyami. Akustichniy visnik, 12 (2), 31–38.
Scheme, E., Castillo-Guerra, E., Englehart, K., Kizhanatham, A. (2006). Practical Considerations for Real-Time Implementation of Speech-Based Gender Detection. Progress in Pattern Recognition, Image Analysis and Applications. Berlin, Heidelberg: Springer, 426–436. doi: http://doi.org/10.1007/11892755_44
Pribil, J., Pribilova, A., Matousek, J. (2016). GMM-based speaker gender and age classification after voice conversion. 2016 First International Workshop on Sensing, Processing and Learning for Intelligent Machines (SPLINE). IEEE, 1–5. doi: http://doi.org/10.1109/splim.2016.7528391
Omelchenko, S. (2018). Development of the method of automatic determination of the speaker gender on the basis of joint evaluation of frequency moments of basic tons and formant frequencies. Technology Audit and Production Reserves, 3 (2 (41)), 29–33. doi: http://doi.org/10.15587/2312-8372.2018.134977
Buyukyilmaz, M., Cibikdiken, A. O. (2016). Voice Gender Recognition Using Deep Learning. Proceedings of 2016 International Conference on Modeling, Simulation and Optimization Technologies and Applications (MSOTA2016). Atlantis Press, 409–411. doi: http://doi.org/10.2991/msota-16.2016.90
Levitan, S. I., Mishra, T., Bangalore, S. (2016). Automatic identification of gender from speech. Proceeding of Speech Prosody, 84–88. doi: http://doi.org/10.21437/speechprosody.2016-18
Faek, F. (2015). Objective Gender and Age Recognition from Speech Sentences. Aro, The Scientific Journal of Koya University, 3 (2), 24–29. doi: http://doi.org/10.14500/aro.10072
Harb, H., Liming, C. (2003). Gender identification using a general audio classifier. 2003 International Conference on Multimedia and Expo. ICME’03. Proceedings (Cat. No.03TH8698). IEEE. doi: http://doi.org/10.1109/icme.2003.1221721
Sorokin, V. N., Makarov, I. S. (2008). Opredelenie pola diktora po golosu. Akusticheskiy zhurnal, 54 (4), 659–668.
Zeng, Y., Wu, Z., Falk, T., Chan, W. (2006). Robust GMM Based Gender Classification using Pitch and RASTA-PLP Parameters of Speech. 2006 International Conference on Machine Learning and Cybernetics. Dalian, 2006. P. 3376–3379. doi: https://doi.org/10.1109/icmlc.2006.258497
Presniakov, I. N., Omel'chenko, S. V. (2003). Pomehoustoichivye algoritmy segmentacii rechi v sistemah obrabotki [Interference-free speech segmentation algorithms in processing systems]. Radiotehnika. Vseukrainskii mezhvedomstvennyi nauchno-tehnicheskii sbornik, 131, 165–173.
Copyright (c) 2019 Sergey Omelchenko
This work is licensed under a Creative Commons Attribution 4.0 International License.
Our journal abides by the Creative Commons CC BY copyright rights and permissions for open access journals.
Authors, who are published in this journal, agree to the following conditions:
1. The authors reserve the right to authorship of the work and pass the first publication right of this work to the journal under the terms of a Creative Commons CC BY, which allows others to freely distribute the published research with the obligatory reference to the authors of the original work and the first publication of the work in this journal.
2. The authors have the right to conclude separate supplement agreements that relate to non-exclusive work distribution in the form in which it has been published by the journal (for example, to upload the work to the online storage of the journal or publish it as part of a monograph), provided that the reference to the first publication of the work in this journal is included.