AI Thrust Seminar | “AI for Good” Applications: Cued Speech and Medical Imagin
“AI for Good” is a relatively new research concept that focuses on using AI to tackle the important social and public health challenges existing today. In this talk, our works about the Cued Speech (CS) and Medical Imaging, which are exactly “AI for Good” applications, will be presented. I will first introduce our research on the automatic recognition of French/English CS, which is a system using the hand codes to complement the natural lip reading to make the hearing-impaired people access spoken language easier. By successfully introducing the deep neural network models into CS automatic recognition for the first time, and conducting research on the CS asynchronous fusion, our works have made significant progress in solving this challenging problem. The first Mandarin Chinese Cued Speech (MCCS) system, which was proposed by us in 2019, will also be introduced. Then, I will introduce our work on AI for Medical Imaging. Based on the clinical medical challenges encountered by the doctors, one of our recent works on semi-supervised active learning for Liver Fibrosis staging will be presented.
Dr. Li Liu is currently a Research Scientist at the Shenzhen Research Institute of Big Data. Before that, she worked as a Postdoc Researcher at the Department of Electrical, Computer and Biomedical Engineering, Ryerson University, Toronto. She obtained her Ph.D. degree in 2018 from Gipsa-lab, University Grenoble Alpes (UGA), Grenoble, France. She has published more than 20 top tier papers as the first author or corresponding author in Audio-visual Speech Processing and AI for Medical Imaging, including IEEE Transactions on Multimedia, American Annals of the Deaf, Neurips, ECCV, ICASSP and MICCAI. In 2017, she won the French Sephora Berribi Scholarship for Female Scientists in Mathematics and Computers (totally four in the world, two in France and two in Israel). In the same year, she was awarded a scholarship for young researchers by the French Voice Association (AFCP). In 2016, she won the best poster award of the French EEATS Graduate School. As PI, she has got 5 competitive research funds, such as the Young Scientists Fund of the Natural Science Foundation of China (NSFC), the Young Scientists Fund of the Natural Science Foundation of Guangdong Province and the Alibaba Innovative Research Fund. Her current research interests include Audio-visual Speech Processing, Cued Speech, and AI for Medical Imaging.