This research article focuses on the performance evaluation of a human voice recognition system utilizing Mel-Frequency Cepstral Coefficients (MFCC) features and a Hidden Markov Model (HMM) classifier. The authors describe the development and testing of a recognition system capable of identifying individuals based on voice input, achieving recognition rates of 80-95% depending on the number of training samples. The paper highlights advancements in voice recognition techniques and emphasizes the significance of HMM for creating speaker-independent systems.