Najim Dehak, an associate professor of electrical and computer engineering, studies machine learning approaches applied to speech processing, audio classification, and health applications. He is a leading developer of the I-vector representation for speaker recognition, and first introduced this state-of-the-art method in 2008 during the Center for Language and Speech Processing’s summer workshop at Johns Hopkins University. Since that time, this approach has become one of the most known speech representations in the entire speech community.
Prior to joining Johns Hopkins, he was a research scientist in the Spoken Language Systems Group at the MIT Computer Science and Artificial Intelligence Laboratory.
Dehak received his PhD from the School of Advanced Technology, Montreal in 2009. He is a senior member of IEEE and a member of the IEEE Speech and Language Technical Committee.