Shruti is a second-year PhD student at the Language Technologies Institute, Carnegie Mellon University, advised by Prof. Florian Metze. Her research aims towards enabling machines to automatically learn from multiple modalities of data like audio, video, speech, text or semantics, as humans naturally do. Prior to starting her PhD, she received her Master’s from Carnegie Mellon University in 2018 and Bachelor’s from Pune Institute of Computer Technology in 2016.
Shruti’s primary research areas are multimodal speech and natural language processing. Human learning is highly multimodal but current machine learning models are task-specific, approaching it as separate problems for speech recognition, text summarization or video understanding. Each of these tasks may benefit if trained jointly leveraging information from different modalities. Her research aims towards achieving this using unsupervised and semi-supervised techniques.
For more information, please visit her website.