About this EventAdd to calendar
Spring 2022 Electrical Engineering and Computer Science (EECS) Seminar Series
Speaker: Shrishail "Shree" Baligar, UC Merced
Title: Audio Analysis using Deep Learning
Host: Shawn Newsam
Recent developments in Deep Learning have brought innovative ways to solve audio signal domain problems that were otherwise dominated by traditional signal processing methods. Additionally, the availability of large audio datasets has allowed for data-driven techniques to solve problems like sound event detection, separation, and other analysis. While sister domains like Computer Vision and Natural Language Processing have contributed to the progress of Audio analysis, there are still challenges and opportunities that are unique to the audio signal. This talk will go over the landscape of problems in the audio signal processing using deep learning, and the specifically the speaker's more recent work on Query-based Audio Source Separation and Detection.
Shrishail Baligar is a Ph.D. Student in Electrical Engineering and Computer Science at the University of California, Merced. His research interests lie in Audio Source Separation and Detection using Deep Learning techniques. In particular, he focuses on Query-based audio source separation and denoising. During his Ph.D., he has worked on real-world problems like the NASA Soundscapes2Landscapes Project, where he deployed an audio event detection model in the wild from the data collected in Sonoma County, California. He is currently also an AI Research Intern at QSC LLC working on Speech Enhancement problems. He will also be at Meta (Facebook) reality labs for the rest of the year as a Research Scientist Intern investigating Audio context understanding problems.
LinkedIn: Shree (https://www.linkedin.com/in/shree-b/)
0 people are interested in this event