Anurag Chowdhury - About me

Hi! I am Anurag, a Ph.D. Candidate in the Department of Computer Science and Engineering at Michigan State University, USA. Here, I work at the iPRoBe lab with my faculty advisor Dr. Arun Ross to develop deep learning models to characterize the acoustic properties of human speech efficiently. Specifically, I develop models that can characterize speaker-dependent speech features from human speech audio recorded in non-ideal audio conditions, such as background noise, channel distortions, and varying speaking styles (such as speaking vs. singing). Current applications of my research include speaker recognition, vocal style transfer, and text to speech synthesis. I am also working on integrating my speaker recognition models with the current state-of-the-art face recognition systems to improve biometric recognition performance in challenging application scenarios, such as adverse illumination conditions.

Academic Background

I am currently pursuing my Ph.D. in Computer Science at Michigan State University, USA. Prior to this, I did my Masters in Technology (M.Tech.) in Computer Science from Indraprastha Institute of Information Technology Delhi (IIIT-Delhi), India, where I was awarded the best Master’s Thesis award for my work on ‘RGB-D face recognition in surveillance videos.’ I received my Bachelor’s in Engineering (B.E.) in Instrumentation and Control Engineering from Netaji Subhas Institute of Technology, University of Delhi, India.