👋 Hello there, I’m Ashish

🎓 Hi, I’m Ashish Seth, a first-year Computer Science Ph.D. student at the University of Maryland, College Park (UMCP). At UMCP, I have the privilege of working under the guidance of Prof. Dinesh Manocha at the Gamma Lab, where my research focuses on enhancing Speech and Audio Understanding in foundation models. My work spans across various problems in speech, language, and audio processing, and I’m passionate about contributing to the field of AI-driven speech/audio understanding.

🖥️ Before beginning my Ph.D. journey, I worked as a Software Engineer at Adobe, India, where I was part of the Marketing Automation Team within the Digital Experience division. My role focused on a segmentation project that leveraged AI to capture and analyze customer and sales insights. The primary goal of this project was to enhance the business-to-business (B2B) marketing experience by refining segmentation processes and making them more intelligent and efficient.

📖 Prior to this, I completed my master in Computer Science and Engineering (CSE) from Indian Institute Of Technology (IIT), Madras, India. During my academic tenure, I was privileged to be a part of Spring Lab, under the guidance of Prof S.Umesh. My contribution within the lab involved development of innovative self-supervised methods for Audio Classification systems. This research culminated in the completion of my master’s thesis, titled “Towards General-Purpose Audio Representation Learning.”

You can find my latest papers in google scholar.