SPS Webinar: Towards Multi-Domain Generalization for Subband Audio Source Separation
Date: 17 April 2025
Time: 11:00 AM ET (New York Time)
Presenter(s): Ms. Karn N. Watcharasupat
Based on the IEEE Xplore® article:
"A Generalized Bandsplit Neural Network for Cinematic Audio Source Separation"
Published: IEEE Open Journal of Signal Processing, December 2023.
Download article: Original article is open access and publicly available for download.
Abstract
Audio source separation is the task of extracting one or more constituent components, or composites thereof, from their mixture. Creatively produced audio signals, such as music and cinematic audio, present a unique challenge for source separation algorithms due to the sheer diversity of potential sound sources within a particular mixture.
However, most state-of-the-art deep learning systems for source separation have often been either a collection of single-source separators or a tightly coupled system that cannot be easily adapted to support additional or unseen sound sources. In this webinar, the presenter will present their series of works on psychoacoustically-motivated subband source separation for music and cinematic audio, working towards a more flexible, extensible, and controllable source separation system that can still maintain the high-fidelity requirements demanded by creative audio practices.
Biography
Karn N. Watcharasupat (S'19, GS'22) received the B.Eng. (Hons) in electrical and electronic engineering from Nanyang Technological University (NTU), Singapore, in 2021, and her M.S. in electrical and computer engineering from Georgia Institute of Technology, Atlanta, GA, USA, in 2024. She is currently pursuing the Ph.D. in music technology at the Music Informatics Group, Georgia Institute of Technology.
She interned with the Audio Algorithms team at Netflix Inc., Los Gatos, CA, USA in 2023 and 2024. Prior to her doctoral studies, she was with the NTU Media Technology Laboratory (2019--2021) and the NTU Digital Signal Processing Laboratory (2020--2022). Since 2021, she has published more than 25 peer-reviewed publications in international conferences and journals spanning the fields of array signal processing, soundscape perception, signal enhancement, music information retrieval, and source separation. Her current research focus is on source separation for music and cinematic audio.
Ms. Watcharasupat currently holds the Google Ph.D. Fellowship in Machine Perception and the IEEE Signal Processing Society Scholarship. Her past awards and honors include the American Association of University Women International Doctoral Degree Fellowship (2023--2024), the NTU Lee Kuan Yew Gold Medal for Electrical and Electronic Engineering (2022), and the Association of Consulting Engineers Singapore Gold Medal (2022). She is a member of the International Society for Music Information Retrieval (ISMIR), the Audio Engineering Society (AES), and the Society of Women Engineers (SWE).
