Multimodal speaker localization from omnidirectional videos.
Pascal ReuseMihai GurbanIvar AustvollJean-Philippe ThiranPublished in: EUSIPCO (2009)
Keyphrases
- audio visual
- multi modal
- mobile robot
- video sequences
- speaker verification
- video frames
- video content
- visual data
- video analysis
- multimodal fusion
- computer vision
- video surveillance
- multimodal interaction
- multimedia
- stereo vision
- omnidirectional camera
- video clips
- vision system
- video database
- object localization
- vision sensor
- speaker diarization
- perspective images
- localization algorithm
- speaker recognition
- image retrieval
- simultaneous localization and mapping
- event recognition
- human activities
- single camera
- spatio temporal
- moving camera
- speech recognition
- video streams
- event detection