Computer Systems and Engineering Seminar Series

Paralinguistic speech attribute recognition and multimodal behavior signal analysis

Speaker:Dr. Ming Li
Date: Monday, November 6, 2017
Time: 12:00pm - 1:00pm
Location: 125 Hudson Hall, Duke
Lunch served at 11:45

Abstract

Speech signal not only contains lexicon information, but also deliver various kinds of paralinguistic speech attribute information, such as speaker, language, gender, age, emotion, channel, voicing, psychological states, etc. The core technique question behind it is utterance level supervised learning based on text independent speech signal with flexible duration. I will select speaker verification as an example to introduce the framework of paralinguistic speech attribute recognition. Moreover, we can extend the signal from speech to multimodal human centered behavior data. I will introduce our works on multimodal behavior signal analysis and interpretation. We apply signal processing and machine learning technologies to human behavior signals, such as audio, visual, physiological and eye tracking data to provide objective and quantitative behavior measurements or codes. Example studies include autism spectrum disorder, obesity, biometrics and piano learning.

Biography

Ming Li received his B.S. degree in communication engineering from Nanjing University, China, in 2005 and his M.S. degree in signal processing from the Institute of Acoustics, Chinese Academy of Sciences, in 2008. He joined the Signal Analysis and Interpretation Laboratory (SAIL) at USC on a Provost fellowship in 2008 and received his Ph.D. in Electrical Engineering in May 2013. He is currently an associate professor at School of Electronics and Information Technology at Sun Yat-Sen University and an adjunct professor at ECE department of Carnegie Mellon University. Ming Li will join Duke Kunshan University on Match 1st 2018 as an Associate Professor. His research interests are in the areas of speech processing and multimodal behavior signal analysis with applications to human centered behavioral informatics notably in health, education and security. He has published more than 70 papers and served as scientific committee members and reviewers for multiple conferences and journals. Works co-authored with his colleagues have won awards at Body Computing Slam Contest 2009, IEEE DCOSS 2009, Interspeech2011-Speaker State Challenge, Interspeech2012-Speaker Trait Challenge, and ISCSLP 2014 best paper award. He received the IBM faculty award at 2016.

Hosted by:
Leslie M. Collins, Ph.D.