Research Interest
My research interest lies at the intersection of machine learning, audio signal processing, and music information retrieval, with a particular focus on multimodal representation learning. I dedicate my efforts to formulating learning-based methodologies predominantly for the processing of audio content, encompassing both musical elements and a variety of other sounds, but not limited to these modalities.
Currently, I am engaged in research on the synchronization of multimodal representations, specifically focusing on integrating motion capture data with music. My work aims to explore and develop applications for this synchronization.
Background
I received my Ph.D. in Electronics and Communication Engineering from the National Institute of Technology Silchar, India in 2022. My Ph.D. thesis is titled “Pattern Recognition Based on Microwave Signal Using Artificial Intelligence” where I worked on the classification of pattern recognition based on an antenna’s reactive field for applications like Human Activity Recognition (HAR) and Machine Health Monitoring.
As a postdoctorate, I joined The Machine Analysis of Data for Human Audition and Visualization (MADHAV) Lab in the Department of Electrical Engineering at the Indian Institute of Technology Kanpur. The group’s research interests lie at the intersection of the theory and application of machine learning with a focus on Machine Learning for Audio Signal Processing. As a trained Western classical guitarist, my research focus naturally shifted towards the application of machine learning in audio signal processing and music information retrieval.
During my postdoctorate, I developed and researched an Audio-based Recommendation System for India’s National Broadcaster, Prasar Bharati, and I played a leading role in handling the deployment of the AI model for Prasar Bharati’s multimedia for efficient search and recommendation.