I am a PhD student at the University of Surrey, UK with research focus on Audio-Visual correspondence learning. Prior to starting my PhD, I was an audio researcher at TCS Research, India, where I worked on a wide range of audio-related topics from spoken lang. understanding, few-shot audio event detection, pathological speech processing etc. My most recent project has been in unsupervised audio-visual segmentation and prior to that diffusion-based denoising approaches for sound event detection. In my next project, I am exploring novel view acoustic synthesis, and visual guided spatial audio synthesis. (more details: https://swapb94.github.io/)