Testing the influence of autonomous system input on human perceptual categorization of speech Joseph D. W. Stephens, Ph.D. Associate Professor Psychology.

Slides:

Advertisements

Similar presentations

Guidebook for Risk Analysis Tools and Management Practices to Control Transportation Project Costs Keith R. Molenaar, PhD Stuart D. Anderson, PhD, PE Transportation.

Advertisements

Data Mining Methodology 1. Why have a Methodology  Don’t want to learn things that aren’t true May not represent any underlying reality ○ Spurious correlation.

Systems Analysis and Design Feasibility Study. Introduction The Feasibility Study is the preliminary study that determines whether a proposed systems.

Effects of pronunciation problems on ESL learners’ listening comprehension Introduction * The importance of listening comprehension * Overview of ESL listeners.

Bivariate Analysis Cross-tabulation and chi-square.

1 Situation Awareness for CFIs Donna Forsyth Wilt, Ph.D. Florida Institute of Technology Presented at CFI Workshop FAA Safety Center, Lakeland, FL May.

Speech Perception Overview of Questions Can computers perceive speech as well as humans? Does each word that we hear have a unique pattern associated.

Elements of Decision Problems

SA-1 Probabilistic Robotics Probabilistic Sensor Models Beam-based Scan-based Landmarks.

Cognitive Processes PSY 334 Chapter 2 – Perception April 9, 2003.

Chapter 12 - Forecasting Forecasting is important in the business decision-making process in which a current choice or decision has future implications:

Instructor: Vincent Duffy, Ph.D. Associate Professor of IE Lecture 9 – Selection & Training Tues. Feb. 13, 2007 IE 486 Work Analysis & Design II.

PSY 369: Psycholinguistics

Organizational Behavior, 9/E Schermerhorn, Hunt, and Osborn Prepared by Michael K. McCuddy Valparaiso University John Wiley & Sons, Inc.

Perceptual Inference and Information Integration in Brain and Behavior PDP Class Jan 11, 2010.

Cognitive Processes PSY 334 Chapter 2 – Perception.

1 MTN-003 Training General Interviewing Techniques Some specific tips for administering the Screening interviewer-administered CRFs SSP Section 14.

Measures of Central Tendency

Creating Empirical Models Constructing a Simple Correlation and Regression-based Forecast Model Christopher Oludhe, Department of Meteorology, University.

Mood and Modality Rajat Kumar Mohanty rkm[AT]cse[DOT]iitb[DOT]ac[DOT]in Centre for Indian Language Technology Department of Computer Science and Engineering.

+ Using Mixed Methods Research Designs for Research in Teaching and Learning Dr. Elizabeth G. Creamer, Virginia Tech Dr. Beth Mac Donald, Utah State University.

Speech Perception. Phoneme - a basic unit of a speech sound that distinguishes one word from another Phonemes do not have meaning on their own but they.

Chapter 7 ©2001 South-Western College Publishing Pamela S. Lewis Stephen H. Goodman Patricia M. Fandt Slides Prepared by Bruce R. Barringer University.

SIMULATION USING CRYSTAL BALL. WHAT CRYSTAL BALL DOES? Crystal ball extends the forecasting capabilities of spreadsheet model and provide the information.

Relational databases and third normal form As always click on speaker notes under view when executing to get more information!

CSCI N207: Data Analysis Using Spreadsheets Copyright ©2005  Department of Computer & Information Science Univariate Data Analysis.

Signal Detection Theory October 10, 2013 Some Psychometrics! Response data from a perception experiment is usually organized in the form of a confusion.

How do university students solve problems in vector calculus? Evidence from eye tracking Karolinska institutet Stockholm 4th of May 2012 Magnus Ögren 1.

Variables, sampling, and sample size. Overview  Variables  Types of variables  Sampling  Types of samples  Why specific sampling methods are used.

Synthetic Cognitive Agent Situational Awareness Components Sanford T. Freedman and Julie A. Adams Department of Electrical Engineering and Computer Science.

Designing for Attention With Sound: Challenges and Extensions to Ecological Interface Design Marcus O. Watson and Penelope M. Sanderson HUMAN FACTORS,

1 IE 590D Applied Ergonomics Lecture 26 – Ergonomics in Manufacturing & Automation Vincent G. Duffy Associate Prof. School of IE and ABE Thursday April.

Additional Statistical Investigations A paired t-test was performed to evaluate whether a perceptual learning process occurs between the initial baseline.

1 MARKETING RESEARCH Week 5 Session A IBMS Term 2,

Epenthetic vowels in Japanese: a perceptual illusion? Emmanual Dupoux, et al (1999) By Carl O’Toole.

How Solvable Is Intelligence? A brief introduction to AI Dr. Richard Fox Department of Computer Science Northern Kentucky University.

Copyright Catherine M. Burns

Introduction to cognitive modeling Marieke van Vugt University of Groningen The Netherlands.

QC THE MULTIRULE INTERPRETATION

Survey – extra credits (1.5pt)! Study investigating general patterns of college students’ understanding of astronomical topics There will be 3~4 surveys.

Instructional Objective  Define an agent  Define an Intelligent agent  Define a Rational agent  Discuss different types of environment  Explain classes.

Chapter 10. The Explorer System in Cognitive Systems, Christensen et al. Course: Robots Learning from Humans On, Kyoung-Woon Biointelligence Laboratory.

U SER I NTERFACE L ABORATORY Situation Awareness a state of knowledge, from the processes used to achieve that state (situation assessment) not encompass.

Correlation They go together like salt and pepper… like oil and vinegar… like bread and butter… etc.

An Overview of the Objectives, Approach, and Components of ComET™ Mr. Paul Price The LifeLine Group All slides and material Copyright protected.

Surveillance and Population-based Prevention Department for Prevention of Noncommunicable Diseases Displaying data and interpreting results.

AP Statistics Chapter 21 Notes

Immersive Virtual Characters for Educating Medical Communication Skills J. Hernendez, A. Stevens, D. S. Lind Department of Surgery (College of Medicine)

When is Cognitive Screening limited?. BRIEF COGNITIVE SCREENING: WHAT IT CAN DO I dentify possible cognitive deficits. Monitor changes in cognition over.

IB Business & Management

Robot Programming from Demonstration, Feedback and Transfer Yoan Mollard, Thibaut Munzer, Andrea Baisero, Marc Toussaint, Manuel Lopes.

Chapter Seventeen Copyright © 2004 John Wiley & Sons, Inc. Multivariate Data Analysis.

Preparing for the Learning Experience Chapter 7. Objectives Discuss the concept of the learning experience Explain the role of the movement practitioner.

UNIT III. A managerial problem can be described as the gap between a given current state of affairs and a future desired state. Problem solving may then.

Chapter 11 Language. Some Questions to Consider How do we understand individual words, and how are words combined to create sentences? How can we understand.

Michelle Hester Advanced Human Factors (PSYC 562)

Technical Report Writing Dr. Shelley Thomas. Overview Selecting effective report topics Using worksheets to plan projects Developing and proposing project.

National Research Lab. An Approach for Assessment of Situation Awareness with Eye Movement and EEG data March, Jun Su Ha Dept. of Nuclear and Quantum.

Does the brain compute confidence estimates about decisions?

King Saud University College of Engineering IE – 341: “Human Factors” Spring – 2016 (2 nd Sem H) Chapter 3. Information Input and Processing Part.

The Interpersonal Mode

Emilie Zamarripa & Joseph Latimer| Faculty Mentor: Jarrod Hines

Cognitive Processes PSY 334

Effects of Oncoming Vehicle Size on Overtaking Judgments

Management of Multiple Dynamic Human Supervisory Control Tasks

Chapter 7 Decision-Making Tools and Techniques Pamela S. Lewis

Cognitive Processes PSY 334

Perceptual Echoes at 10 Hz in the Human Brain

Sybert Stroeve, Henk Blom, Marco van der Park

Presentation transcript:

Testing the influence of autonomous system input on human perceptual categorization of speech Joseph D. W. Stephens, Ph.D. Associate Professor Psychology Department North Carolina A&T State University TECHLAV Seminar Series JDW Stephens Influence of autonomy on perception 25 September

Overview JDW Stephens Influence of autonomy on perception 25 September The importance of Situation Awareness (SA) 2.SA with large-scale autonomous systems 3.The question of uncertainty 4.Pilot study: Testing the influence of uncertain info. 5.Future directions

Overview JDW Stephens Influence of autonomy on perception 25 September The importance of Situation Awareness (SA) 2.SA with large-scale autonomous systems 3.The question of uncertainty 4.Pilot study: Testing the influence of uncertain info. 5.Future directions

The importance of Situation Awareness JDW Stephens Influence of autonomy on perception 25 September What is Situation Awareness? Endsley’s framework (e.g., Endsley, 1995): Level 1 - Perception of elements in environment Level 2 - Comprehension of current situation Level 3 - Projection of future status Importance of Level 1 is not to be underestimated

Overview JDW Stephens Influence of autonomy on perception 25 September The importance of Situation Awareness (SA) 2.SA with large-scale autonomous systems 3.The question of uncertainty 4.Pilot study: Testing the influence of uncertain info. 5.Future directions

SA with large-scale autonomous systems JDW Stephens Influence of autonomy on perception 25 September Let’s consider a light-hearted scenario… Note: This film is being used for illustrative purposes and its use should not be construed as an endorsement!

SA with large-scale autonomous systems JDW Stephens Influence of autonomy on perception 25 September Carl Spackler wants to know where the gophers are … but it’s a big golf course ?

SA with large-scale autonomous systems JDW Stephens Influence of autonomy on perception 25 September What if Carl had a system of robots? …could assist SA Note that there is automation involved in ID

Overview JDW Stephens Influence of autonomy on perception 25 September The importance of Situation Awareness (SA) 2.SA with large-scale autonomous systems 3.The question of uncertainty 4.Pilot study: Testing the influence of uncertain info. 5.Future directions

The question of uncertainty JDW Stephens Influence of autonomy on perception 25 September What if the automation is wrong?

The question of uncertainty JDW Stephens Influence of autonomy on perception 25 September What if the automation is wrong? False Alarm: Not actually a gopher

The question of uncertainty JDW Stephens Influence of autonomy on perception 25 September What if the automation is wrong? Miss: An undetected gopher

The question of uncertainty JDW Stephens Influence of autonomy on perception 25 September Errors (i.e. false alarms, misses) can potentially negate the benefits of automation (Wickens & Dixon, 2007) However, potential for errors cannot be eliminated In dynamic environment, always some uncertainty Current research question: How can human operators interpret information about the uncertainty? Goal: maximize accuracy in Level 1 SA

The question of uncertainty JDW Stephens Influence of autonomy on perception 25 September How does Carl’s SA change if the system tells him about its own uncertainty? 80% 50% 90% 70%

Overview JDW Stephens Influence of autonomy on perception 25 September The importance of Situation Awareness (SA) 2.SA with large-scale autonomous systems 3.The question of uncertainty 4.Pilot study: Testing the influence of uncertain info. 5.Future directions

Pilot Study JDW Stephens Influence of autonomy on perception 25 September As a first step, we are adding uncertain information to a basic categorization task: Consonant identification “Indicate whether you heard ABA or ADA” Can be influenced by visual information from the face of a speaker (e.g., McGurk & MacDonald, 1976) Can also be influenced by artificial visual cues (Stephens & Holt, 2010) What if a computer provides information about the probability of each consonant?

Pilot Study JDW Stephens Influence of autonomy on perception 25 September Stimuli: Five utterances along a series ranging from /aba/ to /ada/ (From the set created by Stephens & Holt, 2011)

Pilot Study JDW Stephens Influence of autonomy on perception 25 September Uncertain information presented on screen “The automated system estimates…” 10% ABA; 90% ADA 30% ABA; 70% ADA 50% ABA; 50% ADA 70% ABA; 30% ADA 90% ABA; 10% ADA XX% ABA; XX% ADA (no information condition) Intermediate sounds were paired with multiple percentages; each combination occurred 15 times

Pilot Study JDW Stephens Influence of autonomy on perception 25 September Preliminary results from n=8 participants No influence of on-screen percentages

Overview JDW Stephens Influence of autonomy on perception 25 September The importance of Situation Awareness (SA) 2.SA with large-scale autonomous systems 3.The question of uncertainty 4.Pilot study: Testing the influence of uncertain info. 5.Future directions

Future directions JDW Stephens Influence of autonomy on perception 25 September Speech categories are extremely familiar Little need to rely on automated system Next experiments will use less familiar categories Explicitly labeled percentages may be ineffective as cues for perception Further experiments will represent uncertain information using other types of visualizations for uncertainty Eventual goal: more realistic SA tasks

Acknowledgments JDW Stephens Influence of autonomy on perception 25 September Christopher Moody TECHLAV NC A&T Psychology Department