Open AccessAge and gender recognition from speech signals
Author(s) -
Assim Ara Abdulsatar,
В. В. Давыдов,
V. V. Yushkova,
A. P. Glinushkin,
V. Yu. Rud
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1410/1/012073
Subject(s) - formant , speech recognition , computer science , classifier (uml) , feature extraction , mel frequency cepstrum , speech processing , artificial intelligence , pattern recognition (psychology) , vowel
The aim of this research is to identify gender and age from speech, the system consists of two parts. The first part is called pre-processing and future extraction. The second part is called classification. This research investigates an automatic gender and age recognizer from speech. First four formant frequencies and twelve MFCCs are used to extract relevant features to recognize the gender. K-NN has been used as a classifier for the age recognizer model, stimulated using MATLAB. A special selectin of solid feature is used in this work to improve the accuracy of the gender and age classifiers based on the frequency range that the features represent.