Shubhr Singh is a Ph.D. student at the UKRI CDT in Artificial Intelligence and Music, specializing in graph neural networks for audio and focusing on environmental sounds and music tasks. Prior to his current academic pursuit, he worked as a strategy consultant at the risk advisory services of prominent big-4 firms. Shubhr holds an MSc in Sound and Music Computing from Queen Mary University of London.
As a Ph.D. student, Shubhr's primary research area revolves around interpreting the complex relationships and dependencies within audio signals leveraging the power of graph based representations and use it to enhance the capabilities of audio systems in recognising and classifying environmental sounds and music information retrieval based tasks.
Shubhr Singh's research focuses on utilising graph neural networks (GNNs) for multivariate time series analysis. GNNs are powerful tools for capturing complex relationships and dependencies within such data. By representing variables as nodes and their relationships as edges in a graph structure, GNNs can effectively model and analyse the data. Shubhr's work aims to leverage this graph representation to extract meaningful features and improve predictions in various domains such as finance, healthcare, and environmental monitoring. His research contributes to advancements in understanding complex systems and making informed decisions based on accurate analysis of multivariate time series data.
