A Visualization System for Evaluating the Degree of Speech Activities in Seminars

Abstract

In recent years, there has been a lot of talk about interactive teaching. Some students are passive in their regular lectures. In an interactive class, the faculty member communicates to that student. In this way, students can discover problems and challenges themselves and are given the opportunity to learn on their own. Seminar can be made better by having interactive classes. We propose a system that can determine the status of the seminar in real time. In this study, we propose a system that creates a spectrogram from recorded speech data of a seminar, identifies speakers by deep learning, and summarizes and displays the results.