| Abstrakt: |
This paper analyzes the effectiveness of the developed voice control system for robotics based on MFCC and GMM-SVM under the influence of interference in the communication channel. The system allows characterizing individual features of speech signals with their subsequent classification and making a reliable decision on the interpretation and execution of voice commands by robotic equipment. The proposed voice control system for robotics based on MFCC and GMM-SVM is implemented using the following technologies: 1) selection of active speech areas by calculating the short-term energy and the number of zero crossings between adjacent frames of the speech signal; 2) adaptive wavelet filtering of the speech signal, where it is necessary to generate threshold values, which will reduce the impact of additive noise; 3) selection of recognition features, which are used as mel-frequency cepstral coefficients; 4) classification of recognition features based on mixtures of Gaussian distributions and the support vector method using the linear Campbell kernel and the principal component method with a projection on latent structures, which will reduce errors of the 1st and 2nd kind. [ABSTRACT FROM AUTHOR] |
