What's Next in Learning for Audio – Going past chasing metrics
Speaker:
Paris Smaragdis (University of Illinois at Urbana-Champaign)
Time & Room:
2022/03/25 (Fri.) 10:00-11:00AM (UTC+8), Zoom ID: 934 1318 5672
In recent years we have seen enormous gains in many audio and speech processing techniques. By making use of deep learning and large data sets we have finally solved many problems to a good degree of audio fidelity. Unfortunately, this has set the attention of the community towards increased performance, and not so much towards solving new problems ad exploring new ideas. In this talk I will present some of the recent work in my group where the goal is to address new ways to process audio, while addressing real-life problems. I will talk about efficiency, distributed learning, meta-learning, and unsupervised learning approaches, and how we can use these in the context of concrete applications.
Paris Smaragdis is a Professor and Associate Head at the Computer Science Department at the University of Illinois at Urbana-Champaign. He completed his masters, PhD, and postdoctoral studies at MIT, performing research on computational audition. In 2006 he was selected by MIT's Technology Review as one of the year's top young technology innovators for his work on machine listening, in 2015 he was elevated to an IEEE Fellow for contributions in audio source separation and audio processing, and during 2016-2017 he is an IEEE Signal Processing Society Distinguished Lecturer. He has authored more than 150 papers on various aspects of audio signal processing, holds more than 50 patents worldwide, and his research has been productized by multiple companies. He has previously been the chair of the LVA/ICA community, and the chair of the IEEE Machine Learning for Signal Processing Technical Committee, the chair of the IEEE Audio and Acoustics Signal Processing Technical Committee, a senior area editor of IEEE Transactions of Signal Processing, and a member of IEEE Signal Processing Society's Board of Governors. He is currently the Editor in Chief for the ACM/IEEE Transactions of Audio, Speech and Language Processing.
