I understand that you require classify the extracted coefficients from the 'mfcc' function using SVM.
You can achieve the desired result using the 'fitcsvm' using the coefficients and labels available for classification.
You can follow this example:
% Considering 'coeffs' as the variable for coefficients extracted from the 'mfcc' function
% Considering 'labels' as the variable for prediction labels
% Training the SVM classifier
SVMModel = fitcsvm(coeffs, labels, 'KernelFunction', 'linear', 'Standardize', true);
% Individual classifier parameters can be changed according to the use-case.
The 'predict' function can be used to obtain the predictions of the trained model on untrained data.
You can refer to the folowing Mathworks documentations to know more about these functions:
Hope this helps!
