Gender Recognition by Voice and Speech Analysis

Developed a Gender Recognition project using voice and speech analysis techniques, leveraging a dataset comprising 3,168 recorded voice samples from male and female speakers.
Utilized acoustic analysis in R with seewave and tuneR packages to preprocess voice samples, extracting features such as mean frequency, standard deviation of frequency, median frequency, and spectral entropy within the human vocal range (0hz-280hz). Implemented machine learning algorithms to classify voice samples as male or female based on extracted features, achieving accurate gender recognition results through feature analysis and model training.