Since May 2016, I have started working as an Assistant Professor at Bangladesh University of Engineering and Technology. Previously, I worked as a Research Scientist at Robert Bosch Research and Technology Center (RTC) in Silicon Valley, CA. I did my PhD in Electrical Engineering from The University of Texas at Dallas, and worked in the Center of Robust Speech Systems (CRSS) group. My PhD advisor was Dr. John H.L. Hansen. I did my BS and MS in Electrical and Electronic Engineering from Bangladesh University of Engineering and Technology (BUET)
ResearchMy research goal is to advance signal processing and machine learning techniques for information extraction from speech, audio and video signals. My past work focused on: 1) speaker verification (voice authentication) in noisy, telephone/microphone channel degraded and non-stationary acoustic conditions, 2) speech enhancement and front-end improvement, 3) automatic highlight generation for sports videos using audio-visual features.
|Our article on "Acoustic Factor Analysis" (AFA) paradigm was featured in the cover of IEEE Transactions on Audio, Speech, and Language Processing.||Visualizing Maximum-Likelihood Acoustic Factor Analysis training using 2-D data. Presented in our follow-up IEEE article on AFA.||Automatically generated highlights from a Baseball game using audio-visual features. The methods are presented in our paper here.|
Media CoverageOur research work on the NIST speaker recognition evaluation 2012 was covered by the UTD News Center on Sep 4, 2013. Our paper on this work won a student paper award in ICASSP-2013.
I'm also an occasional singer/songwriter. A music album containing my original songs was released by the record label G-series in Bangladesh. You can check out my songs in ReverbNation, and videos in Youtube and Facebook. I was also the lead singer and guitarist of the Bengali rock band Dhumketu in Dallas, TX.