Due to its widespread application in a variety of circumstances, the gender classification system has become more and more relevant including social media platforms and criminal investigations. Prior studies in this area have mostly focused on discrimination against both men and women. Nevertheless, since transgender persons have just received legal recognition, it has been vital to create techniques for accurately diagnosing gender from a specific voice, which can be a challenging undertaking. To extract pertinent characteristics from a training set that may be utilised to create a model for gender categorization, researchers have employed a number of techniques. Following then, a vocal signal’s gender may be ascertained using this model. The study makes three significant contributions: first, it provides a thorough analysis of well-known voice signal features using a well-known dataset; second, it investigates a variety of machine learning models from a variety of theoretical families to classify voice gender; and third, it uses three well-known feature selection algorithms to select the features that have the greatest potential to improve classification models.