I am currently a researcher under Prof. C. V. Jawahar at the Applied Research Lab, CVIT, IIIT-Hyderabad . My current work is on weakly supervised lipreading using deep neural networks. I am experimenting with convolutional and recurrent neural networks to achieve standard benchmarks in visual speech recognition.
Previously, I worked as an Image Processing Engineer at GreyOrange Robotics in the Embedded Systems team. I was involved in designing computer vision modules for real time video processing and pattern recognition for warehouse automation and autonomos robots. Before that, I worked in Airbus, India, in the Avionics Software and Systems Testing group. I was involved in development and validation of avionincs systems in the Flight Warning Computer for aircrafts in the long-range family.
I graduated from IIT Kharagpur, India, in 2014 with a Dual Degree (B.Tech. (H) + M.Tech.) in Electrical Engineering, my Master’s specialization being Instrumentation and Signal Processing. My Bachelor’s and Master’s thesis were in the areas of computer vision, image processing, machine learning.
To work at the intersection of computer vision and machine learning towards artificial intelligence; to understand and apply learning techniques such as deep neural networks to vision-related research.