Audio machine learning
Budget: $30 – $250 CAD
Greetings,
I've developed code for the classification and recognition of two primary speakers based on MFCC and GFCC audion features and using GMM, SVM, CNN, and DNN models. While the project's code is finished, the achieved accuracy is unsatisfactory and necessitates refinement. Consequently, I am seeking assistance from someone capable of enhancing the accuracy of real-time experimentation. Additionally, I require support in visualizing the outputs of each model and conducting a comparative analysis of their results. Kindly refrain from reaching out to propose a complete code overhaul, as I will not entertain such offers. Moreover, if you lack familiarity with GMM, SVM, CNN, and DNN, kindly refrain from contacting me in this regard.
I've developed code for the classification and recognition of two primary speakers based on MFCC and GFCC audion features and using GMM, SVM, CNN, and DNN models. While the project's code is finished, the achieved accuracy is unsatisfactory and necessitates refinement. Consequently, I am seeking assistance from someone capable of enhancing the accuracy of real-time experimentation. Additionally, I require support in visualizing the outputs of each model and conducting a comparative analysis of their results. Kindly refrain from reaching out to propose a complete code overhaul, as I will not entertain such offers. Moreover, if you lack familiarity with GMM, SVM, CNN, and DNN, kindly refrain from contacting me in this regard.