I am currently pursuing my degree for Masters in Computer Science at University of California San Diego. Before this, I was working as a Research Assistant at the IIITD ALIVE project under the guidance of Saket Anand, Jainendra Shukla and Rajiv Ratn Shah. My aim is to facilitate the conceptualization and deployment of complex computer vision systems that can handle real-world uncertainty and are compact and efficient.
Download my resumé.
Working on the development and testing of the Perception software stack for the autonomous vehicle:
Worked on the development of Near Real-Time RAN Intelligence Controller (RIC)
Worked on using deep neural networks for Natural Language Processing
This paper presents SpeechMix, a regularization and data augmentation technique for deep sound recognition. Our strategy is to create virtual training samples by interpolating speech samples in hidden space. SpeechMix has the potential to generate an infinite number of new augmented speech samples since the combination of speech samples is continuous. Thus, it allows downstream models to avoid overfitting drastically. Unlike other mixing strategies that only work on the input space, we apply our method on the intermediate layers to capture a broader representation of the feature space. Through an extensive quantitative evaluation, we demonstrate the effectiveness of SpeechMix in comparison to standard learning regimes and previously applied mixing strategies. Furthermore, we highlight how different hidden layers contribute to the improvements in classification using an ablation study.
Worked on several parts of the autonomous driving software stack. The projects along with their github links are listed below. For detailed information on the projects, please refer to the repositories.