ENTERFACE 08 Project 1 “MultiParty Communication with a Tour Guide ECA” Mid-term presentation August 19th, 2008.

Slides:



Advertisements
Similar presentations
National Technical University of Athens Department of Electrical and Computer Engineering Image, Video and Multimedia Systems Laboratory
Advertisements

Pseudo-Relevance Feedback For Multimedia Retrieval By Rong Yan, Alexander G. and Rong Jin Mwangi S. Kariuki
Face Alignment by Explicit Shape Regression
OpenDial Framework Svetlana Stoyanchev SDS seminar 3/23.
ENTERFACE’08 Multimodal Communication with Robots and Virtual Agents.
University of Minho School of Engineering Centre ALGORITMI Uma Escola a Reinventar o Futuro – Semana da Escola de Engenharia - 24 a 27 de Outubro de 2011.
Presented by Sam Supervised by Prof. Michael Lyu.
23-May-151 Multiparty Communication with a Tour Guide ECA Aleksandra Čereković HOTLab group Department of telecommunications Faculty of electrical engineering.
Didier Perroud Raynald Seydoux Frédéric Barras.  Abstract  Objectives  Modalities ◦ Project modalities ◦ CASE/CARE  Implementation ◦ VICI, Iphone,
Chapter 3 Nonverbal Communication. What is nonverbal communication? “Everything that communicates a message but does not use words” Facial expressions,
Review for Midterm Exam - Mgmt 464 Winter Bring Scantrons for the midterm.
Supervised by Prof. LYU, Rung Tsong Michael Department of Computer Science & Engineering The Chinese University of Hong Kong Prepared by: Chan Pik Wah,
Department of Computer Science and Engineering, CUHK 1 Final Year Project 2003/2004 LYU0302 PVCAIS – Personal Video Conference Archives Indexing System.
Communicating with Avatar Bodies Francesca Barrientos Computer Science UC Berkeley 8 July 1999 HCC Research Retreat.
1 Final Year Project 2003/2004 LYU0302 PVCAIS – Personal Video Conference Archives Indexing System Supervisor: Prof Michael Lyu Presented by: Lewis Ng,
1 IUT de Montreuil Université Paris 8 Emotion in Interaction: Embodied Conversational Agents Catherine Pelachaud.
Emotional Intelligence and Agents – Survey and Possible Applications Mirjana Ivanovic, Milos Radovanovic, Zoran Budimac, Dejan Mitrovic, Vladimir Kurbalija,
Sunee Holland University of South Australia School of Computer and Information Science Supervisor: Dr G Stewart Von Itzstein.
Building the Design Studio of the Future Aaron Adler Jacob Eisenstein Michael Oltmans Lisa Guttentag Randall Davis October 23, 2004.
Vision-Based Biometric Authentication System by Padraic o hIarnain Final Year Project Presentation.
Knowledge Systems Lab JN 8/24/2015 A Method for Temporal Hand Gesture Recognition Joshua R. New Knowledge Systems Laboratory Jacksonville State University.
What is Concurrent Programming? Maram Bani Younes.
GUI: Specifying Complete User Interaction Soft computing Laboratory Yonsei University October 25, 2004.
Methods For Web Page Design 6. Methods Why use one? What it covers –Possibly all stages Feasibility Analysis Design Implementation Testing –Maybe just.
Software Development Stephenson College. Classic Life Cycle.
Recognition of meeting actions using information obtained from different modalities Natasa Jovanovic TKI University of Twente.
Expressive Emotional ECA ✔ Catherine Pelachaud ✔ Christopher Peters ✔ Maurizio Mancini.
Chapter 7. BEAT: the Behavior Expression Animation Toolkit
APML, a Markup Language for Believable Behavior Generation Soft computing Laboratory Yonsei University October 25, 2004.
Department of Computer Science and Engineering, CUHK 1 Final Year Project 2003/2004 LYU0302 PVCAIS – Personal Video Conference Archives Indexing System.
Emotional Embodied Conversational Agent Name : Ranjeet Singh FAN : sing0258 Student-Id :
Department of Computer Science and Engineering, CUHK 1 Final Year Project 2003/2004 LYU0302 PVCAIS – Personal VideoConference Archives Indexing System.
Greta MPEG-4 compliant Script based behaviour generator system: Script based behaviour generator system: input - BML or APML input - BML or APML output.
ENTERFACE 08 Project 2 “multimodal high-level data integration” Mid-term presentation August 19th, 2008.
卓越發展延續計畫分項三 User-Centric Interactive Media ~ 主 持 人 : 傅立成 共同主持人 : 李琳山,歐陽明,洪一平, 陳祝嵩 水美溫泉會館研討會
Issues in Multiparty Dialogues Ronak Patel. Current Trend  Only two-party case (a person and a Dialog system  Multi party (more than two persons Ex.
Can We Talk?: Building Social Communication Skills Lydia H. Soifer, Ph.D. SPED*NET Wilton Norwalk SPED Partners.
A Common Ground for Virtual Humans: Using an Ontology in a Natural Language Oriented Virtual Human Architecture Arno Hartholt (ICT), Thomas Russ (ISI),
ENTERFACE ’08 Project 2 “Multimodal High Level Data Integration” Final Report August 29th, 2008.
HYMES (1964) He developed the concept that culture, language and social context are clearly interrelated and strongly rejected the idea of viewing language.
1 Natural Language Processing Lecture Notes 14 Chapter 19.
Intelligent Robot Architecture (1-3)  Background of research  Research objectives  By recognizing and analyzing user’s utterances and actions, an intelligent.
1 Chapter 12. Web Information Integration Using Multiple Character Agents Soft computing Laboratory Yonsei University October 27, 2004.
Österreichisches Forschnungsinstitut für Artificial Intelligence Representational Lego for ECAs Brigitte Krenn.
Feedback Elisabetta Bevacqua, Dirk Heylen,, Catherine Pelachaud, Isabella Poggi, Marc Schröder.
4 November 2000Bridging the Gap Workshop 1 Control of avatar gestures Francesca Barrientos Computer Science Division UC Berkeley.
Therapeutic Communication
Week 04 Object Oriented Analysis and Designing. What is a model? A model is quicker and easier to build A model can be used in simulations, to learn more.
QuizMASter – A Multi-Agent Game-Style Learning Activity Mark Dutchuk Vancouver Island University, Canada Khalid Aziz Muhammadi Government of Alberta, Canada.
1 Galatea: Open-Source Software for Developing Anthropomorphic Spoken Dialog Agents S. Kawamoto, et al. October 27, 2004.
How to Become an Effective Speaker and Writer
ENTERFACE 08 Project #1 “ MultiParty Communication with a Tour Guide ECA” Final presentation August 29th, 2008.
The Social Robots Project
Immersive Virtual Characters for Educating Medical Communication Skills J. Hernendez, A. Stevens, D. S. Lind Department of Surgery (College of Medicine)
ENTERFACE’08 Multimodal Communication with Robots and Virtual Agents mid-term presentation.
Conversational role assignment problem in multi-party dialogues Natasa Jovanovic Dennis Reidsma Rutger Rienks TKI group University of Twente.
Stanford hci group / cs376 u Jeffrey Heer · 19 May 2009 Speech & Multimodal Interfaces.
W3C Multimodal Interaction Activities Deborah A. Dahl August 9, 2006.
WP6 Emotion in Interaction Embodied Conversational Agents WP6 core task: describe an interactive ECA system with capabilities beyond those of present day.
© 2011 Cengage Learning. All Rights Reserved. CHAPTER 11 Speech Delivery 11.1Effective Speech Delivery 11.2Delivery, Rehearsal, and Audience Adaptation.
1 COMMUNICATION SKILLS UNT in partnership with TEA. Copyright ©. All rights reserved.
Communication and Interpersonal Skills By Adel Ali 18/09/14371Communication Skills, Adel Ali.
NCP meeting Jan 27-28, 2003, Brussels Colette Maloney Interfaces, Knowledge and Content technologies, Applications & Information Market DG INFSO Multimodal.
KRISTINA Consortium Presented by: Mónica Domínguez (UPF-TALN)
Supervisor: Prof Michael Lyu Presented by: Lewis Ng, Philip Chan
Approaches to Discourse Analysis
Multimodal Caricatural Mirror
Project #2 Multimodal Caricatural Mirror Intermediate report
Presented by: Mónica Domínguez
Presentation transcript:

eNTERFACE 08 Project 1 “MultiParty Communication with a Tour Guide ECA” Mid-term presentation August 19th, 2008

Outline Project Summary (Repeating the lesson ;) ) System configuration Work in progress Speech Regonition Nonverbal Input Handling Input Understanding Dialogue Management Character Animation Player Conclusion

Summary We aim to create an ECA based system which will interract with two users by: Capturing their behaviors (speech, nonverbal behaviors) Combining and handling input data Generating and displaying response to these behaviors in the real time

Input Speech recognition Nonverbal behavior detection (Face detection, Facial orientiation, Hand raising) Central Part Input Understanding, Dialogue Management Output ECA animation player Platform to provide communication between the components System Configuration

Speech Recognition Two SR components will be running on different machines Keywords will be dynamically changed according the conversational state No significant overlapping between microphones (distance ~ 1.5 m) Implementation in progress: Keywords detection with confidence score and speech duration by using Loquendo API

Implemented: System which uses OpenCV to calculate difference between the frames to detect the appearance of users To do: Hand raising to ask the question by using OpenCV (If time permits) Nonverbal Inputs: Appearance of the User and Hand Raising

Implemented: Facial Orientation Detection Work in progress : Face tracking: Users are starting mutual conversation or leaving the system? Nonverbal Inputs: Face Orientation

Input Understanding Component Combines two verbal channels and image processing data to recognize users’ utterances Examples: who is speaking, who is adressee, are users’ starting mutual conversation...? Component is still in early stage since input components are not being implemented

Dialogue Management Component - Functionalities Make decisions “when and what to do to whom”: Handle multi-modal input events Handle user interruptions while the agent is doing something Keep a model of each user Keep the domain knowledge, discourse model, and context memory Generate multi-modal outputs

Dialogue Management Component - Progress Dialogue management component based on information state theory [Larsson’00] in still being implemented The progress of dialogue is represented by a set of variables These variables are updated or queried by a basic unit called dialogue move like ask, answer, repeat, inform Conversation strategies (plans) can be composed to respond to different circumstance Most appropriate plan are selected and scheduled by simple inference

Dialogue Management Component - Issues What to do when the agent is interrupted by the user? What to do when speech recognition fails? What to do when the users are talking to each other? What to do when the users starts to talk to the system at the same time? How ECA’s gaze direction can be controlled? How grounding can be implemented using verbal and non- verbal information? What to do when the response of the user is not what the system expected?

Character Animation Player Character animation (ECA) player generates speech and synchronized animation by using XML based GSML language Multiple threads in animation player obtain speech and gesture synchrony Set of animations implemented Gazing, beats, facial expressions (joy, sad...), symbolic gestures To do: construct ECA behaviors according the system scenario (canned behaviors, general states)

Character Animation Player: Example

Conclusion We are in (slow :S) progress To integrate a baseline system we need to implement: SR component Component to detect facial orientation Input Understanding DM component Behavior specification script for character Player Expected Outcome: there are many...