SlideShare una empresa de Scribd logo
1 de 26
2 December 2005
Fusion in Multimodal Interactive Systems:
An HMM-Based Algorithm for User-Induced
Adaptation
Bruno Dumas1, Beat Signer1 and Denis Lalanne2
1 WISE Research Lab, Vrije Universiteit Brussel, Belgium
2 DIVA Research Group, University of Fribourg, Switzerland
Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 2
June 26, 2012
Outline
• Fusion of multimodal input
• Multimodal interaction: from design to implementation
• Algorithms for fusion of multimodal input
• A Hidden Markov Model-based fusion algorithm
• Instantiation of the algorithm
• Evaluation of the algorithm
• Qualitative test
• Quantitative evaluation
• Performance assessment
• Conclusion
Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 3
June 26, 2012
Fusion of Multimodal Input
 Challenges in multimodal interaction engineering:
continous and probabilistic inputs, real-time…
Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 4
June 26, 2012
Challenging/Ambiguous Fusion Cases
• “Put-that-there”
 Complementarity case
• “Play next track”
 Different meanings based on order and context
Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 5
June 26, 2012
CARE Properties at the Design Level
 Describe how modalities can be combined
 Complementarity
 All modalities are necessary
 Assignment
 Absence of choice
 Redundancy
 Same expressive power between modalities
 Equivalence
 Any modality is sufficient
Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 6
June 26, 2012
HephaisTK Multimodal Framework
Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 7
June 26, 2012
Description of Multimodal Dialogues
• Syntactic-level description
• For more details: check
SMUIML language
Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 8
June 26, 2012
Fusion Algorithms
• Frame-based algorithms & Unification-
based algorithms
• Symbolic approaches
• Both are a de facto standard
• Symbolic-statistical algorithms
Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 9
June 26, 2012
Symbolic-Statistical Approaches
 Symbolic data
 Interpretation of low-level data
 Statistical processing
 Machine learning algorithms
Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 10
June 26, 2012
Our HMM-Based Fusion Algorithm
 Why hidden Markov models?
 Very good modelling of time-related events
 Takes advantage of input data coming from
probabilistic input modalities
 On-the-fly adaptation of the model
- e.g. based on user feedback
Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 11
June 26, 2012
Put-That-There Example
Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 12
June 26, 2012
Put-That-There Example
Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 13
June 26, 2012
Put-That-There Example
Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 14
June 26, 2012
Put-That-There Example
Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 15
June 26, 2012
Put-That-There Example
Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 16
June 26, 2012
Put-That-There Example
Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 17
June 26, 2012
Instantiation of the Algorithm
Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 18
June 26, 2012
Evaluation of the Algorithm
 Evaluation on three levels
 Qualitative “gut check” test
 Benchmarks on real-world examples
 Performance assessment
Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 19
June 26, 2012
Evaluation: Qualitative Test
• Three expert users were asked to assess the
behaviour of the algorithm
 frames-based and HMM-based fusion
 5 minutes per condition + interview
• Coherent behaviour between the algorithms
• No noticeable difference
in responsiveness
Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 20
June 26, 2012
Evaluation: Benchmark
Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 21
June 26, 2012
Evaluation: Benchmark
Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 22
June 26, 2012
Benchmark Results (1)
• CARE properties: equivalence and redundancy tests
Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 23
June 26, 2012
Benchmark Results (2)
• Sequential and non-sequential complementarity tests
Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 24
June 26, 2012
Benchmark Results (3)
• “Play next track” example
Meaning
frames
HMM-based
Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 25
June 26, 2012
Evaluation: Performance
• Per fusion algorithm:
• 5 runs of 40 input pieces
• 5 x 20 expected fusion results
• Frame-based: 18.2 ms
• Standard deviation: 12.7 ms
• HMM-based: 16.6 ms
• Standard deviation: 11.6 ms
Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 26
June 26, 2012
Conclusion
• A new symbolic-statistical multimodal fusion
algorithm based on Hidden Markov Models
• Integrated into the HephaisTK framework
• Superior recognition rates compared to existing
algorithms
• Handling of ambiguous cases
• Processing of real-time user feedback
http://wise.vub.ac.be/bruno-dumas

Más contenido relacionado

Similar a Fusion in Multimodal Interactive Systems: An HMM-Based Algorithm for User-Induced Adaptation

21st century skills 03FEB15
21st century skills 03FEB1521st century skills 03FEB15
21st century skills 03FEB15Janine Kiers
 
Bb on Tour 2016 | Innovation and Your Institution (Part 2) – Open Source Road...
Bb on Tour 2016 | Innovation and Your Institution (Part 2) – Open Source Road...Bb on Tour 2016 | Innovation and Your Institution (Part 2) – Open Source Road...
Bb on Tour 2016 | Innovation and Your Institution (Part 2) – Open Source Road...Blackboard APAC
 
BPM Cluster Meeting 2018
BPM Cluster Meeting 2018BPM Cluster Meeting 2018
BPM Cluster Meeting 2018Jan Claes
 
ECIR Recommendation Challenges
ECIR Recommendation ChallengesECIR Recommendation Challenges
ECIR Recommendation ChallengesDaniel Kohlsdorf
 
Validation of Design Tools-PPT for CEDAR Meeting-04-15-2016
Validation of Design Tools-PPT for CEDAR Meeting-04-15-2016Validation of Design Tools-PPT for CEDAR Meeting-04-15-2016
Validation of Design Tools-PPT for CEDAR Meeting-04-15-2016Varun Singh
 
Lecture_2_Deep_Learning_Overview (1).pptx
Lecture_2_Deep_Learning_Overview (1).pptxLecture_2_Deep_Learning_Overview (1).pptx
Lecture_2_Deep_Learning_Overview (1).pptxgamajima2023
 
BIM, Big Data and Mashup in Architectural Computing – Experimenting with Digi...
BIM, Big Data and Mashup in Architectural Computing – Experimenting with Digi...BIM, Big Data and Mashup in Architectural Computing – Experimenting with Digi...
BIM, Big Data and Mashup in Architectural Computing – Experimenting with Digi...Stefan Boeykens
 
Selection of an appropriate project approach
Selection of an appropriate project approachSelection of an appropriate project approach
Selection of an appropriate project approachtumetr1
 
Challenges of Cloud Monitoring
Challenges of Cloud MonitoringChallenges of Cloud Monitoring
Challenges of Cloud MonitoringWilliam Pourmajidi
 
Privacy and Security in Multi-modal User Interface Modeling for Social Media
Privacy and Security in Multi-modal User Interface Modeling for Social MediaPrivacy and Security in Multi-modal User Interface Modeling for Social Media
Privacy and Security in Multi-modal User Interface Modeling for Social Mediamsm2011socialcom
 
Usability evaluation methods (part 2) and performance metrics
Usability evaluation methods (part 2) and performance metricsUsability evaluation methods (part 2) and performance metrics
Usability evaluation methods (part 2) and performance metricsAndres Baravalle
 
Course Review - Lecture 13 - Introduction to Databases (1007156ANR)
Course Review - Lecture 13 - Introduction to Databases (1007156ANR)Course Review - Lecture 13 - Introduction to Databases (1007156ANR)
Course Review - Lecture 13 - Introduction to Databases (1007156ANR)Beat Signer
 
Innovation day 2012 16. koenraad rombaut & michiel de paepe - verhaert - mo...
Innovation day 2012   16. koenraad rombaut & michiel de paepe - verhaert - mo...Innovation day 2012   16. koenraad rombaut & michiel de paepe - verhaert - mo...
Innovation day 2012 16. koenraad rombaut & michiel de paepe - verhaert - mo...Verhaert Masters in Innovation
 
Introduction to mechatronics
Introduction to mechatronicsIntroduction to mechatronics
Introduction to mechatronicsAmeya Nijasure
 
Apresentação no 4o Workshop de Sistemas Distribuídos Autonômicos - WoSiDA 201...
Apresentação no 4o Workshop de Sistemas Distribuídos Autonômicos - WoSiDA 201...Apresentação no 4o Workshop de Sistemas Distribuídos Autonômicos - WoSiDA 201...
Apresentação no 4o Workshop de Sistemas Distribuídos Autonômicos - WoSiDA 201...Sandro Andrade
 
Model driven engineering for big data management systems
Model driven engineering for big data management systemsModel driven engineering for big data management systems
Model driven engineering for big data management systemsMarcos Almeida
 

Similar a Fusion in Multimodal Interactive Systems: An HMM-Based Algorithm for User-Induced Adaptation (20)

21st century skills 03FEB15
21st century skills 03FEB1521st century skills 03FEB15
21st century skills 03FEB15
 
Bb on Tour 2016 | Innovation and Your Institution (Part 2) – Open Source Road...
Bb on Tour 2016 | Innovation and Your Institution (Part 2) – Open Source Road...Bb on Tour 2016 | Innovation and Your Institution (Part 2) – Open Source Road...
Bb on Tour 2016 | Innovation and Your Institution (Part 2) – Open Source Road...
 
BPM Cluster Meeting 2018
BPM Cluster Meeting 2018BPM Cluster Meeting 2018
BPM Cluster Meeting 2018
 
ECIR Recommendation Challenges
ECIR Recommendation ChallengesECIR Recommendation Challenges
ECIR Recommendation Challenges
 
MBUID survey
MBUID surveyMBUID survey
MBUID survey
 
Lecture-2 Applied ML .pptx
Lecture-2 Applied ML .pptxLecture-2 Applied ML .pptx
Lecture-2 Applied ML .pptx
 
Validation of Design Tools-PPT for CEDAR Meeting-04-15-2016
Validation of Design Tools-PPT for CEDAR Meeting-04-15-2016Validation of Design Tools-PPT for CEDAR Meeting-04-15-2016
Validation of Design Tools-PPT for CEDAR Meeting-04-15-2016
 
Lecture_2_Deep_Learning_Overview (1).pptx
Lecture_2_Deep_Learning_Overview (1).pptxLecture_2_Deep_Learning_Overview (1).pptx
Lecture_2_Deep_Learning_Overview (1).pptx
 
BIM, Big Data and Mashup in Architectural Computing – Experimenting with Digi...
BIM, Big Data and Mashup in Architectural Computing – Experimenting with Digi...BIM, Big Data and Mashup in Architectural Computing – Experimenting with Digi...
BIM, Big Data and Mashup in Architectural Computing – Experimenting with Digi...
 
Selection of an appropriate project approach
Selection of an appropriate project approachSelection of an appropriate project approach
Selection of an appropriate project approach
 
Challenges of Cloud Monitoring
Challenges of Cloud MonitoringChallenges of Cloud Monitoring
Challenges of Cloud Monitoring
 
Privacy and Security in Multi-modal User Interface Modeling for Social Media
Privacy and Security in Multi-modal User Interface Modeling for Social MediaPrivacy and Security in Multi-modal User Interface Modeling for Social Media
Privacy and Security in Multi-modal User Interface Modeling for Social Media
 
Usability evaluation methods (part 2) and performance metrics
Usability evaluation methods (part 2) and performance metricsUsability evaluation methods (part 2) and performance metrics
Usability evaluation methods (part 2) and performance metrics
 
Course Review - Lecture 13 - Introduction to Databases (1007156ANR)
Course Review - Lecture 13 - Introduction to Databases (1007156ANR)Course Review - Lecture 13 - Introduction to Databases (1007156ANR)
Course Review - Lecture 13 - Introduction to Databases (1007156ANR)
 
Innovation day 2012 16. koenraad rombaut & michiel de paepe - verhaert - mo...
Innovation day 2012   16. koenraad rombaut & michiel de paepe - verhaert - mo...Innovation day 2012   16. koenraad rombaut & michiel de paepe - verhaert - mo...
Innovation day 2012 16. koenraad rombaut & michiel de paepe - verhaert - mo...
 
CASCON06.ppt
CASCON06.pptCASCON06.ppt
CASCON06.ppt
 
Formal Method
Formal Method Formal Method
Formal Method
 
Introduction to mechatronics
Introduction to mechatronicsIntroduction to mechatronics
Introduction to mechatronics
 
Apresentação no 4o Workshop de Sistemas Distribuídos Autonômicos - WoSiDA 201...
Apresentação no 4o Workshop de Sistemas Distribuídos Autonômicos - WoSiDA 201...Apresentação no 4o Workshop de Sistemas Distribuídos Autonômicos - WoSiDA 201...
Apresentação no 4o Workshop de Sistemas Distribuídos Autonômicos - WoSiDA 201...
 
Model driven engineering for big data management systems
Model driven engineering for big data management systemsModel driven engineering for big data management systems
Model driven engineering for big data management systems
 

Último

Moving Beyond Passwords: FIDO Paris Seminar.pdf
Moving Beyond Passwords: FIDO Paris Seminar.pdfMoving Beyond Passwords: FIDO Paris Seminar.pdf
Moving Beyond Passwords: FIDO Paris Seminar.pdfLoriGlavin3
 
Varsha Sewlal- Cyber Attacks on Critical Critical Infrastructure
Varsha Sewlal- Cyber Attacks on Critical Critical InfrastructureVarsha Sewlal- Cyber Attacks on Critical Critical Infrastructure
Varsha Sewlal- Cyber Attacks on Critical Critical Infrastructureitnewsafrica
 
So einfach geht modernes Roaming fuer Notes und Nomad.pdf
So einfach geht modernes Roaming fuer Notes und Nomad.pdfSo einfach geht modernes Roaming fuer Notes und Nomad.pdf
So einfach geht modernes Roaming fuer Notes und Nomad.pdfpanagenda
 
React Native vs Ionic - The Best Mobile App Framework
React Native vs Ionic - The Best Mobile App FrameworkReact Native vs Ionic - The Best Mobile App Framework
React Native vs Ionic - The Best Mobile App FrameworkPixlogix Infotech
 
2024 April Patch Tuesday
2024 April Patch Tuesday2024 April Patch Tuesday
2024 April Patch TuesdayIvanti
 
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024BookNet Canada
 
Decarbonising Buildings: Making a net-zero built environment a reality
Decarbonising Buildings: Making a net-zero built environment a realityDecarbonising Buildings: Making a net-zero built environment a reality
Decarbonising Buildings: Making a net-zero built environment a realityIES VE
 
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyesHow to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyesThousandEyes
 
Bridging Between CAD & GIS: 6 Ways to Automate Your Data Integration
Bridging Between CAD & GIS:  6 Ways to Automate Your Data IntegrationBridging Between CAD & GIS:  6 Ways to Automate Your Data Integration
Bridging Between CAD & GIS: 6 Ways to Automate Your Data Integrationmarketing932765
 
A Deep Dive on Passkeys: FIDO Paris Seminar.pptx
A Deep Dive on Passkeys: FIDO Paris Seminar.pptxA Deep Dive on Passkeys: FIDO Paris Seminar.pptx
A Deep Dive on Passkeys: FIDO Paris Seminar.pptxLoriGlavin3
 
The State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptxThe State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptxLoriGlavin3
 
Data governance with Unity Catalog Presentation
Data governance with Unity Catalog PresentationData governance with Unity Catalog Presentation
Data governance with Unity Catalog PresentationKnoldus Inc.
 
Genislab builds better products and faster go-to-market with Lean project man...
Genislab builds better products and faster go-to-market with Lean project man...Genislab builds better products and faster go-to-market with Lean project man...
Genislab builds better products and faster go-to-market with Lean project man...Farhan Tariq
 
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptxPasskey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptxLoriGlavin3
 
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptxUse of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptxLoriGlavin3
 
A Framework for Development in the AI Age
A Framework for Development in the AI AgeA Framework for Development in the AI Age
A Framework for Development in the AI AgeCprime
 
The Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsThe Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsPixlogix Infotech
 
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...Wes McKinney
 
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxMerck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxLoriGlavin3
 
[Webinar] SpiraTest - Setting New Standards in Quality Assurance
[Webinar] SpiraTest - Setting New Standards in Quality Assurance[Webinar] SpiraTest - Setting New Standards in Quality Assurance
[Webinar] SpiraTest - Setting New Standards in Quality AssuranceInflectra
 

Último (20)

Moving Beyond Passwords: FIDO Paris Seminar.pdf
Moving Beyond Passwords: FIDO Paris Seminar.pdfMoving Beyond Passwords: FIDO Paris Seminar.pdf
Moving Beyond Passwords: FIDO Paris Seminar.pdf
 
Varsha Sewlal- Cyber Attacks on Critical Critical Infrastructure
Varsha Sewlal- Cyber Attacks on Critical Critical InfrastructureVarsha Sewlal- Cyber Attacks on Critical Critical Infrastructure
Varsha Sewlal- Cyber Attacks on Critical Critical Infrastructure
 
So einfach geht modernes Roaming fuer Notes und Nomad.pdf
So einfach geht modernes Roaming fuer Notes und Nomad.pdfSo einfach geht modernes Roaming fuer Notes und Nomad.pdf
So einfach geht modernes Roaming fuer Notes und Nomad.pdf
 
React Native vs Ionic - The Best Mobile App Framework
React Native vs Ionic - The Best Mobile App FrameworkReact Native vs Ionic - The Best Mobile App Framework
React Native vs Ionic - The Best Mobile App Framework
 
2024 April Patch Tuesday
2024 April Patch Tuesday2024 April Patch Tuesday
2024 April Patch Tuesday
 
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
 
Decarbonising Buildings: Making a net-zero built environment a reality
Decarbonising Buildings: Making a net-zero built environment a realityDecarbonising Buildings: Making a net-zero built environment a reality
Decarbonising Buildings: Making a net-zero built environment a reality
 
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyesHow to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
 
Bridging Between CAD & GIS: 6 Ways to Automate Your Data Integration
Bridging Between CAD & GIS:  6 Ways to Automate Your Data IntegrationBridging Between CAD & GIS:  6 Ways to Automate Your Data Integration
Bridging Between CAD & GIS: 6 Ways to Automate Your Data Integration
 
A Deep Dive on Passkeys: FIDO Paris Seminar.pptx
A Deep Dive on Passkeys: FIDO Paris Seminar.pptxA Deep Dive on Passkeys: FIDO Paris Seminar.pptx
A Deep Dive on Passkeys: FIDO Paris Seminar.pptx
 
The State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptxThe State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptx
 
Data governance with Unity Catalog Presentation
Data governance with Unity Catalog PresentationData governance with Unity Catalog Presentation
Data governance with Unity Catalog Presentation
 
Genislab builds better products and faster go-to-market with Lean project man...
Genislab builds better products and faster go-to-market with Lean project man...Genislab builds better products and faster go-to-market with Lean project man...
Genislab builds better products and faster go-to-market with Lean project man...
 
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptxPasskey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptx
 
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptxUse of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
 
A Framework for Development in the AI Age
A Framework for Development in the AI AgeA Framework for Development in the AI Age
A Framework for Development in the AI Age
 
The Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsThe Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and Cons
 
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...
 
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxMerck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
 
[Webinar] SpiraTest - Setting New Standards in Quality Assurance
[Webinar] SpiraTest - Setting New Standards in Quality Assurance[Webinar] SpiraTest - Setting New Standards in Quality Assurance
[Webinar] SpiraTest - Setting New Standards in Quality Assurance
 

Fusion in Multimodal Interactive Systems: An HMM-Based Algorithm for User-Induced Adaptation

  • 1. 2 December 2005 Fusion in Multimodal Interactive Systems: An HMM-Based Algorithm for User-Induced Adaptation Bruno Dumas1, Beat Signer1 and Denis Lalanne2 1 WISE Research Lab, Vrije Universiteit Brussel, Belgium 2 DIVA Research Group, University of Fribourg, Switzerland
  • 2. Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 2 June 26, 2012 Outline • Fusion of multimodal input • Multimodal interaction: from design to implementation • Algorithms for fusion of multimodal input • A Hidden Markov Model-based fusion algorithm • Instantiation of the algorithm • Evaluation of the algorithm • Qualitative test • Quantitative evaluation • Performance assessment • Conclusion
  • 3. Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 3 June 26, 2012 Fusion of Multimodal Input  Challenges in multimodal interaction engineering: continous and probabilistic inputs, real-time…
  • 4. Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 4 June 26, 2012 Challenging/Ambiguous Fusion Cases • “Put-that-there”  Complementarity case • “Play next track”  Different meanings based on order and context
  • 5. Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 5 June 26, 2012 CARE Properties at the Design Level  Describe how modalities can be combined  Complementarity  All modalities are necessary  Assignment  Absence of choice  Redundancy  Same expressive power between modalities  Equivalence  Any modality is sufficient
  • 6. Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 6 June 26, 2012 HephaisTK Multimodal Framework
  • 7. Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 7 June 26, 2012 Description of Multimodal Dialogues • Syntactic-level description • For more details: check SMUIML language
  • 8. Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 8 June 26, 2012 Fusion Algorithms • Frame-based algorithms & Unification- based algorithms • Symbolic approaches • Both are a de facto standard • Symbolic-statistical algorithms
  • 9. Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 9 June 26, 2012 Symbolic-Statistical Approaches  Symbolic data  Interpretation of low-level data  Statistical processing  Machine learning algorithms
  • 10. Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 10 June 26, 2012 Our HMM-Based Fusion Algorithm  Why hidden Markov models?  Very good modelling of time-related events  Takes advantage of input data coming from probabilistic input modalities  On-the-fly adaptation of the model - e.g. based on user feedback
  • 11. Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 11 June 26, 2012 Put-That-There Example
  • 12. Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 12 June 26, 2012 Put-That-There Example
  • 13. Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 13 June 26, 2012 Put-That-There Example
  • 14. Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 14 June 26, 2012 Put-That-There Example
  • 15. Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 15 June 26, 2012 Put-That-There Example
  • 16. Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 16 June 26, 2012 Put-That-There Example
  • 17. Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 17 June 26, 2012 Instantiation of the Algorithm
  • 18. Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 18 June 26, 2012 Evaluation of the Algorithm  Evaluation on three levels  Qualitative “gut check” test  Benchmarks on real-world examples  Performance assessment
  • 19. Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 19 June 26, 2012 Evaluation: Qualitative Test • Three expert users were asked to assess the behaviour of the algorithm  frames-based and HMM-based fusion  5 minutes per condition + interview • Coherent behaviour between the algorithms • No noticeable difference in responsiveness
  • 20. Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 20 June 26, 2012 Evaluation: Benchmark
  • 21. Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 21 June 26, 2012 Evaluation: Benchmark
  • 22. Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 22 June 26, 2012 Benchmark Results (1) • CARE properties: equivalence and redundancy tests
  • 23. Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 23 June 26, 2012 Benchmark Results (2) • Sequential and non-sequential complementarity tests
  • 24. Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 24 June 26, 2012 Benchmark Results (3) • “Play next track” example Meaning frames HMM-based
  • 25. Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 25 June 26, 2012 Evaluation: Performance • Per fusion algorithm: • 5 runs of 40 input pieces • 5 x 20 expected fusion results • Frame-based: 18.2 ms • Standard deviation: 12.7 ms • HMM-based: 16.6 ms • Standard deviation: 11.6 ms
  • 26. Bruno Dumas – WISE resarch lab – Department of Computer Science - bdumas@vub.ac.be 26 June 26, 2012 Conclusion • A new symbolic-statistical multimodal fusion algorithm based on Hidden Markov Models • Integrated into the HephaisTK framework • Superior recognition rates compared to existing algorithms • Handling of ambiguous cases • Processing of real-time user feedback http://wise.vub.ac.be/bruno-dumas