The Course Will Present The Speech Signal and How It Is Represented For Machine Learning Systems. The Course Will Be Foucsed On The Most Recent Advances in Automatic Speech Recognition, Speech Representation, and Speech Synthesis. Learning Outcomes# at The End of The Course The Students Will Know# 1. Will Understand How Speech Is Generated and What Are The Acousic Components of The Speech Signal._ 2. Will Understand How Speech Is Represented in Deep Neural Network Systems. 3. Will Familiar With The Most Recent Models For Automatic Speech Recognition. 4. Will Familiear With The Most Recent Models For Speech Synthesis.

Faculty: Electrical and Computer Engineering
|Graduate Studies

Pre-required courses

46195 - Machine Learning or 236756 - Introduction to Machine Learning


Semestrial Information