User Interface Technologies (UIT) centers around the emerging and future interface technologies that support Human Computer Interaction (HCI). UIT research focuses on the enabling technologies that help computers hear (speech & speaker recognition and verification), see (face, gesture, gaze & handwriting recognition and object tracking), speak (speech synthesis, facial synthesis), and sense (affect recognition, sensor technologies); and to understand and combine these in multimodal ways. Please use the project links below for detailed information on the individual areas of UIT.
Projects
- Audio/Visual Recognition
Joint processing of audio and visual information for speech and speaker recognition
- Collaborative User Experience
- Computational Media Aesthetics
Bridging the Semantic Gap in Video Analysis using a Media Production-guided Approach
- Conversational Biometrics
Speaker Verification Through Conversation
- E-Learning Content Management
Enabling generic content repositories for standards-compliant e-learning content store and management
- Embedded Applications: Pen, Handwriting and Multimodel Technologies
Handwriting recognition
- Embedded Concatenative Text to Speech (eCTTS)
Construct a small footprint embedded concatenative Text to Speech system suitable for implementation on embedded platforms.
- Everywhere Displays
Steerable Interaces for Smart Spaces
- Exploratory Computer Vision
- Human Language Technologies
Sounds in user interface design
- PeopleVision
Visual Tracking for Smart Surveillance
- Speaker Recognition
Speaker verification
- TrackPoint
In-Keyboard Pointing Device
- Voicemail
Word error rate (WER) on voicemail transcription
- Web Intermediaries (WBI)
Web Application Frameworks, Personalization