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

Abstract

<p><em>The object of research is the methods of recognizing the speaker gender by means of speech signals. One of the most problematic places is insufficient knowledge of the choice of signs and decisive rules. This is necessary to increase the probability of correct recognition and noise immunity of gender recognition by voice signals in conditions of interference. It is also important to simplify the implementation of algorithms for recognizing the speaker gender.</em></p><p><em>For recognition of the speaker gender, a new set of classification characteristics is selected, including the joint use of estimates of the average value of the pitch frequency, its kurtosis coefficient, estimates of the mean values of the formants and their asymmetry coefficients. In the course of the research, the method of statistical testing of the proposed algorithms on a personal computer is used. The experiments are carried out using real audio signals input from a microphone into a personal computer for both female and male representatives, and recorded as separate files. For this purpose, 10 standards of 10 words are used for each of the 5 female speakers and 5 male speakers.</em></p><p><em>Based on the results of statistical tests for an algorithm involving the joint use of estimates of the mean value of the pitch frequency, its kurtosis coefficient, estimates of the mean values of the formants and their asymmetry coefficients, an average probability of correct recognition is obtained 1. With the additional action of additive noise of the Gaussian type, white noise and the ratio of the signal/noise q=20, for such algorithm the probability of correct recognition is experimentally obtained – 0.8. For the decision algorithm, which uses only estimates of the average value of the pitch frequency and its kurtosis coefficient, an average probability of correct recognition is estimated at 0.9. This indicates more noise immunity of such algorithms.</em></p><p><em>In the future, the use of the obtained results not only for Russian and Ukrainian languages, but also for a number of foreign languages is supposed.</em></p>

Authors and Affiliations

Sergey Omelchenko

Keywords

Related Articles

Use of energy management as a strategic direction of sustainable development of an organization

<p><em>The object of the study is energy management, which activity is directed on providing the rational use of fuel-energetic resources at an enterprise or municipalities that allows to optimize volumes of energy consu...

Formation of system frameworks of energy controlling

<p><em>The object of research is the controlling concept and its application in the energy sector of the enterprise. Controlling concept opens wide perspectives and provides economic instruments to raise effectiveness an...

Intestigation of the effect of a mixture of sprouted grains on the quality and nutritional value of bakery products

<p><em>The object of research in the work is wheat bread, enriched with a mixture of sprouted grains. In sprouted grains due to the technology of soaking, the process of sprouting and drying, natural properties are prese...

Development of dynamic model of forming investment value of resources in information systems of integrated service networks

<p><em>The object of research is the investment value of pricing policy, maximizing investment profit in the developed information system. One of the most problematic places is determining the cost of adjusting the input...

Analysis of the theoretical and methodological support of the study of energy security of the country

<p><em>World energy consumption is constantly growing. In these conditions, the problem of finding new opportunities to meet the growing needs in energy resources is becoming more acute. This situation leads to the need...

Download PDF file
  • EP ID EP527428
  • DOI 10.15587/2312-8372.2018.134977
  • Views 120
  • Downloads 0

How To Cite

Sergey Omelchenko (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. Технологический аудит и резервы производства, 3(2), 29-33. https://europub.co.uk/articles/-A-527428