Seminar by Prof. Wonyong Sung, Bio-Signal Processing - Standing on the Shoulders of Speech Recognition Technology (12 Dec 2023)

12 Dec 2023 10.00 AM - 12.00 PM Industry/Academic Partners

You are cordially invited to the following Seminar hosted by
Professor Gan Woon Seng (EEE)

Date and Time:
12 Dec 2023 (Tue) | 10:00am – 12:00pm

Venue:
NTU EEE Executive Seminar Room (S2.2-B2-53)

Title:
Bio-Signal Processing - Standing on the Shoulders of Speech Recognition Technology

Speaker:
Prof. Wonyong Sung

Abstract:
Over the past decade, we have witnessed remarkable strides in automatic speech recognition technology. Speech recognition technology has been transformed from statistical models to sophisticated deep neural network-based end-to-end algorithms. Today, our attention turns to bio-signal processing, a field with vast potential for enhancing human health. Several applications within bio-signal processing, such as ECG, PPG, and EEG can be seen as sequential classification algorithms, with automatic speech recognition technology being one of the most well-studied examples. 

This presentation shows the possibility of advancing bio-signal processing by harnessing automatic speech recognition technology. To illustrate this concept, I will provide a case study focused on sleep stage classification using electrocardiogram (ECG) signals. Traditionally, ECG-based sleep classification relied heavily on manually selected features. In contrast, our approach leverages deep neural networks inspired by the speech recognition models. Specifically, we introduce a sleep model, which resembles the language models used in speech recognition. Furthermore, I will share preliminary results for CTC-loss-based deep neural network training, including its implications for data collection.

Biography:

Prof. Wonyong Sung is an Emeritus Professor at Seoul National University. His research interests are speech recognition with deep neural networks, and also deep neural network model compression. His works on speech recognition have been published in top-ranking AI conferences, such as ICML(2016), NeurIPS (2017, 2018), and ICLR(2022). His recent research area is bio-signal processing with deep neural networks.

He worked for the School of Electrical and Computer Engineering of Seoul National University from 1989 to 2020. He also worked for the School of AI in GIST (Gwangju Institute of Science and Technology) as a distinguished visiting professor. He received the Google AI-focused research awards from 2019 to 2022. His current research is supported by the National Research Foundation of Korea (NRF) grant (No.2021R1A2C1013513). He is an IEEE Fellow. Additionally, he served as the chair of the Design and Implementation of Signal Processing (DISPS) Technical Committee of the IEEE Signal Processing Society.

Categories