Herme: An experimental/dialog platform Ciaran Dougherty Trinity College Dublin, Centre for Language Communication Studies, Speech Communications Lab.

Slides:



Advertisements
Similar presentations
Touch-Screen Mobile- Device Data Collection for Biometrics Studies W. Ciaurro, B. Major, D. Martinez, D. Panchal, G. Perez, M. Rana, R. Rana, R. Reyes,
Advertisements

                      Digital Audio 1.
Digital Story Telling MSET April 20, A Picture Worth a 1000 Words If a picture is worth a thousand words – just think how effectively your sudents.
Antelope Relational Database Management System A practical introduction.
ENTERFACE’08 Multimodal Communication with Robots and Virtual Agents.
Human interaction is not constructed as a single channel – it is multimodal. Speech and gestures correlate to convey meaning. Moreover, human interaction.
Sensor-based Situated, Individualized, and Personalized Interaction in Smart Environments Simone Hämmerle, Matthias Wimmer, Bernd Radig, Michael Beetz.
Heterogeneous Multi-Robot Dialogues for Search Tasks Thomas K Harris, Satanjeev (Bano) Banerjee Alexander Rudnicky AAAI Spring Symposium 2005: Dialogical.
The State of the Art in VoiceXML Chetan Sharma, MS Graduate Student School of CSIS, Pace University.
A Social and Emotional Approach to Games and Human Computer Interaction (HCI) Katherine Isbister Associate Professor, Digital Media and CSE.
1 A Framework for Mobile, Context-Aware Trails-based Applications: Experiences with an Applications-led Approach Cormac Driver.
CS335 Principles of Multimedia Systems Multimedia and Human Computer Interfaces Hao Jiang Computer Science Department Boston College Nov. 20, 2007.
Orientation to Online Learning An Instructors Guide.
OHT 1.1 Galin, SQA from theory to implementation © Pearson Education Limited 2004 The uniqueness of software quality assurance The environments for which.
Communicating with Avatar Bodies Francesca Barrientos Computer Science UC Berkeley 8 July 1999 HCC Research Retreat.
Next Generation Desktop Environment Project Looking Glass 3D Farrukh Shakil CS /02/06.
Find The Better Way Expand Your Voice with VXML May 10 th, 2005.
Sunee Holland University of South Australia School of Computer and Information Science Supervisor: Dr G Stewart Von Itzstein.
Biointelligence Laboratory School of Computer Science and Engineering Seoul National University Cognitive Robots © 2014, SNU CSE Biointelligence Lab.,
Natural Language Processing and Speech Enabled Applications by Pavlovic Nenad.
1 A Practical Rollout & Tuning Strategy Phil Shinn 08/06.
Usability Testing. Testing Methods Same as Formative Surveys/questionnaires Interviews Observation Documentation Automatic data recording/tracking Artificial/controlled.
Bring your Friends to the Party: Incorporating Guest Speakers into your Online Course! Christopher Neidig & Daniel Shpak Quinnipiac University Christopher.
1 © 2006 Cisco Systems, Inc. All rights reserved. Cisco Confidential: DO NOT DISTRIBUTE Cisco TelePresence ROI Analysis Findings Your Name Your Title Date.
Multiple Autonomous Ground/Air Robot Coordination Exploration of AI techniques for implementing incremental learning. Development of a robot controller.
Speech Recognition Robot
INTERACTING WITH SIMULATION ENVIRONMENTS THROUGH THE KINECT Fayez Alazmi Supervisor: Dr. Brett Wilkinson Flinders University Image 1Image 2 Source : 1.
GENERAL PRESENTATION SUBMITTED BY:- Neeraj Dhiman.
Real-Time Operating Systems An Overview of RoBIOS.
Group Members: Sam Marlin, Jonathan Brown Faculty Adviser: Tom Miller.
Visual and Specialised Interfaces. 3D Software Developments have led to visual systems such as pictures of the earth’s structure and reproductions of.
Interactive Spaces Huantian Cao Department of Computer Science The University of Georgia.
Project By: Brent Elder, Mike Holovka, Hisham Algadaibi.
Applied Linguistics Nick Campbell & Hideki Kashioka learning how people speak.
Lecture 15 – Social ‘Robots’. Lecture outline This week Selecting interfaces for robots. Personal robotics Chatbots AIML.
Accessible Mainstream Products AT Act Projects April 29, 2010 Jim Tobias, Inclusive Technologies.
ENTERFACE 08 Project 1 “MultiParty Communication with a Tour Guide ECA” Mid-term presentation August 19th, 2008.
User-System Interaction: from gesture to action Prof. dr. Matthias Rauterberg IPO - Center for User-System Interaction TU/e Eindhoven University of Technology.
Intelligent Robot Architecture (1-3)  Background of research  Research objectives  By recognizing and analyzing user’s utterances and actions, an intelligent.
Evaluating the User Interface of a Ubiquitous Computing system Doorman Kaj Mäkelä Tampere University Computer Human Interaction Group.
Persuasion Terms. Logos- The process of reasoning that uses logic, numbers facts and data. Pathos- When the writer appeals to the reader’s emotions Ethos-
AAC and Acquired Disorders. Aphasia There are different types of aphasia. With aphasia there is a rehabilitation period. There is a Psychological Impact.
VoiceXML Version 2.0 Jon Pitcherella. What is it? A W3C standard for specifying interactive voice dialogues. Uses a “voice” browser to interpret documents,
MIT Artificial Intelligence Laboratory — Research Directions The Next Generation of Robots? Rodney Brooks.
User Responses to Prosodic Variation in Fragmentary Grounding Utterances in Dialog Gabriel Skantze, David House & Jens Edlund.
Immersive Virtual Characters for Educating Medical Communication Skills J. Hernendez, A. Stevens, D. S. Lind Department of Surgery (College of Medicine)
University of West Bohemia Faculty of Applied Sciences Department of Cybernetics Enterface 2008 Milos Zelezny –
Chapter 1 Outline - The uniqueness of software quality assurance - The environments for which SQA methods are developed.
A Gesture Based System Humanize Technology.  Communication is the way we learn.  What about learners with communication difficulties?  Make technology.
Microsoft Research Faculty Summit Dan Bohus, Eric Horvitz Microsoft Research.
Speech data in Swedish national archives and government agencies Jens Edlund, KTH Royal Institute of Technology Dept. of Speech, Music and Hearing.
Humanoid-Human Interaction Presented by KMR ANIK 1.
TOUCHLESS TOUCHSCREEN USER INTERFACE
Preliminary project assignment Smart house Natural User Interface for Business NUIT4B.
 ASMARUL SHAZILA BINTI ADNAN  Word Emotion comes from Latin word, meaning to move out.  Human emotion can be recognize from facial expression,
Outline  What is MySmartEye ?  Motivation, objectives.  Implementation.  Programming techniques.  Future Work.  Demo.
Nicole looks at faces Development of a visual robot interface to interpret facial expressions NICOLE: Future robots will share their environment with humans.
Derek Hunt Education Commons
2016 Maintenance Innovation Challenge
Natural Language Processing and Speech Enabled Applications
Inclusive Digital Materials
SYSTEM ANALYSIS AND DESIGN
Derek Hunt Education Commons

Design & Evaluation Methods
Real-Time Vision-Based Gesture Learning for Human-Robot
Lab 3: Isolated Word Recognition
The SharpPlot Chart Wizard
Microsoft Cognitive Services with Power BI
VoiceXML An investigation Author: Mya Anderson
Presentation transcript:

Herme: An experimental/dialog platform Ciaran Dougherty Trinity College Dublin, Centre for Language Communication Studies, Speech Communications Lab

Herme Built using LegoNXT robot platform Microphones, Cameras Currently in TCD's Science Gallery Live since April

Goals Study human/device interactions Better understand the unique differences between human/human dialogs and human/machine dialogs Experiment with tricks to maintain “engagement”

Problems Isolating audio in Real World environments  DIT has tech which can do, can't afford. False positives, negatives in facial recognition software Hardware problems  Overheating, interoperability Subject/Dialog problems Recording problems

(Preliminary) Results Timing data from Wizard of Oz Subjective improvement through use of turn grabbers People seem to accept generic phrases as most cooperative interpretations  Solidifying & limiting script...including with greetings and “dismissals” Employees, who know better, treat Herme as a person

Prognosis Currently implementing new inputs  Motion detection  Improved speech detection? Weaning away from WOZ, using timing data  Attempt to use Timing data with similar, but different script Analyze data to compare gestures to human/human interactions

Questions?