Klasifikasi Rentang Usia Dan Gender Dengan Deteksi Suara Menggunakan Metode Deep Learning Algoritma Cnn (Convolutional Neural Network)

Abstract

The research discusses the identification of human voices based on gender by utilizing the differences in voice characteristics between males and females. In addition to differences in vocal tract size, factors such as length, thickness, and stiffness of the vocal cords also play a role in producing the differences in fundamental frequency between the two genders. Fundamental frequency serves as an indicator used in acoustic analysis to classify gender based on voice. In the automatic classification of voices, sound processing techniques and machine learning are key in system development. Gender recognition methods based on voice involve acoustic analysis using voice features such as fundamental frequency, formants, duration, intensity, and intonation patterns. Diverse voice datasets containing recordings of both male and female voices are used to train gender recognition models. From the results of research from modeling using CNN on audio to get 92% accuracy and for testing results it is good enough in classifying. Keywords – Deep Learning, Voice Recognition, Audio Classification, CNN, Gender