Prof. Soo-Young Lee
Korea Advanced Institute of Science and Technology, South Korea
Speech Title: Audio-Visual Emotion Recognition and Expression for Mindful Conversational Agents
Abstract：For the successful interaction between human and digital companion, i.e., machine agents, the digital companions need to have human-like personality as well as to make emotional dialogue, understand human emotion, and express its own emotion. In this talk we will report our continuing efforts and recent results to develop human-like emotional conversational agents as a part of the Korean National Flagship AI Program. The emotion of human users is estimated from text, audio, and visual face expression during verbal conversation, and the emotion of intelligent agents is expressed in the speech and facial images. We will first show how our ensemble of neural networks won the Emotion Recognition in the Wild (EmotiW2015) challenge with 61.6% accuracy to recognize seven emotions from facial expression. Then, the top-down attention mechanism provides multimodal integration of text, voice, and facial images for better accuracy and explainability. Also, a deep learning based Text-to-Speech (TTS) system will be introduced to express emotions in the dialogue as well as the personal speech styles. These emotions of human users and agents interact each other during the conversation. The agents respond differently for different emotional states in chitchat mode. Then, the emotion as an internal state will be further extended into trustworthiness, implicit intention, preference, and personality, which will also be included in the conversational interactions for much better bindings between human and agents.
Introduction to Prof. Soo-Young Lee:
Soo-Young Lee is Founder of AI Consulting, Inc., CTO of Artificial Language Intelligence, Inc. (ALI), Professor Emeritus of Korea Advanced Institute of Science and Technology (KAIST), and a Fellow of International Neural Network Society (INNS). For the last 30 years he has worked on intelligent machine, i.e., Artificial Intelligence, inspired by brain information processing mechanism. He is now leading Emotional Conversational Agent Project, a Korean National Flagship AI Project, with about 20 professors and 5 organizations. His companies are specialized to provide consulting and R&D services in speech processing, natural language understanding, conversational agents for industries. He was President of Asia-Pacific Neural Network Society, and had received Presidential Award from INNS and Outstanding Achievement Award from APNNA. His research interests have resided in the artificial cognitive systems with human-like intelligent and emotional behavior. He has worked on speech and image recognition, natural language processing, situation awareness, internal-state recognition, and human-like conversational agents. Among many internal states, he is interested in emotion, sympathy, trust, ethics, and personality. His group marked Top-1 for the emotion recognition challenge from facial images (EmotiW; Emotion Recognition in the Wild) in 2015 and 3rd ranked at ConvAI2017 challenge. His Text-To-Speech (TTS) technology enables human-like speech generation with emotion and personality.
Dr. Swagatam Das
Electronics and Communication Sciences Unit, Indian Statistical Institute, Kolkata, India.
Speech Title: Large-scale and Multi-peak Optimization with Differential Evolution - Some Recent Approaches and Future Challenges.
Abstract: Differential Evolution (DE) is arguably one of the most powerful stochastic optimization algorithms of current interest. Since its inception in 1995, DE has drawn the attention of many researchers all over the world resulting in a lot of variants of the basic algorithm with improved performance, especially on continuous parametric spaces. This talk will begin with a brief but comprehensive overview of the basic concepts related to DE, its algorithmic components and control parameters. It will subsequently discuss some of the significant algorithmic variants of DE for bound-constrained single-objective optimization for high-dimensional search spaces. The talk will then focus on some interesting DE variants with additional mechanisms like a distance-based selection, a clustering procedure and bi-objective formulations for solving multi-peak optimization problems where the objective is to locate all the global and local optima of a fitness landscape during one run of the algorithm. The talk will finally highlight a few open research problems in the related areas.
Introduction to Dr.Swagatam Das:
Swagatam Das is currently serving as an associate professor at the Electronics and Communication Sciences Unit of the Indian Statistical Institute, Kolkata, India. His research interests include machine learning and non-convex optimization. Dr. Das has published one research monograph, one edited volume, and more than 300 research articles in peer-reviewed journals and international conferences. He is the founding co-editor-in-chief of Swarm and Evolutionary Computation, an international journal from Elsevier. He has also served as or is serving as the associate editors of Pattern Recognition (Elsevier), IEEE Trans. on Systems, Man, and Cybernetics: Systems, IEEE Computational Intelligence Magazine, IEEE Access, Neurocomputing (Elsevier), Engineering Applications of Artificial Intelligence (Elsevier), and Information Sciences (Elsevier). He is an editorial board member of Applied Soft Computing (Elsevier) and Progress in Artificial Intelligence (Springer). Dr. Das has 19000+ Google Scholar citations and an H-index of 64 till date. He has acted as guest editors for special issues in journals like IEEE Transactions on Evolutionary Computation and IEEE Transactions on SMC, Part C. He is the recipient of the 2012 Young Engineer Award from the Indian National Academy of Engineering (INAE). He is also the recipient of the 2015 Thomson Reuters Research Excellence India Citation Award as the highest cited researcher from India in Engineering and Computer Science category between 2010 to 2014.