Parkinson’s Disease (PD) is a neurodegenerative illness with progressive symptoms, including tremors, stiffness, and bradykinesia. Early diagnosis and continuous monitoring are critical for managing the disease and improving the quality of life of more than 10 million people globally affected by PD. By employing state-of-the-art techniques in the domain of automatic speech signal analysis, less invasive and cost-efficient diagnosis and monitoring of Parkinson’s disease (PD) is possible. Studies report that approximately 90% of patients with PD show some voice disorder, including pitch, amplitude, or speech rate modulation. Specifically, this study applies machine learning methods to audio recordings of PD patients and healthy controls from datasets of willing participants with more than 830 total audio recordings. Extracted features like pitch, jitter, shimmer, and harmonics-to-noise ratio, and then used these features extracted from speech signal as input in classification methods that achieved accuracy levels in classification over 97%. The ultimate goal of this research would be to develop a non-invasive, simple, reliable, and valid assessment tool for clinicians so early detection of PD may create continuous monitoring procedures.