Overview

This is part of the reasearch and development of an Intelligent Voice Commands Detection system at Sharif Data Analytics Lab. under supervision of Dr. S. A. Motahari. Throughout the work, my main task was the development of a speaker verification system, in which the authentication is done by user’s voice. For this purpose, I trained and evaluated the state‑of‑the‑art ECAPA‑TDNN model on Common Voice Persian dataset. The experiment results are available on GitHub.