Muscle - Audio-Visual Automatic Speech Recognition (AV-ASR)

Workpackages

WP2: Evaluation, Integration and Standards

WP3: Visual Content Indexing

WP4: Content Description for Audio, Speech and Text

WP5: Multimodal Processing and Interaction

WP6: Machine Learning and Computation Applied to Multimedia

WP7: Dissemination towards Industry


Workpackages
Overview
E-teams
Fellowships
Roadmaps
Deliverables
Softwares
Papers


Showcases
Courseware
Book Projects
Press Release
Download Logo


Latest news
Previous news


Past events
Sponsored events


Objectives
Documents & Deliverables
Demos & Resources
Meetings
E-teams
Members


Objectives
Documents & Deliverables
Demos & Resources
Meetings
E-teams
Members


Objectives
Documents & Deliverables
Demos & Resources
Meetings
E-teams
Members


Objectives
Documents & Deliverables
Demos & Resources
Meetings
E-teams
Members


Objectives
Documents & Deliverables
Meetings
E-teams
Members


Objectives
Documents & Deliverables
Demos & Resources
Meetings
E-teams
Members
Industrial Contacts and Publicity

Audio-Visual Automatic Speech Recognition (AV-ASR)

Contact person: Petros Maragos (ICCS-NTUA)
Synopsis:

AV Feature Extraction
Feature Fusion
Dynamical Models for AV-ASR
Evaluation

Keywords:

feature extraction, speech recognition, multimodal, audio-visual, feature fusion, dynamical modelling, evaluation

Additonal info: E-Team's webpage