Visually Assisted Self-supervised Audio Speaker Localization and Tracking.
Jinzheng ZhaoPeipei WuShidrokh GoudarziXubo LiuJianyuan SunYong XuWenwu WangPublished in: EUSIPCO (2022)
Keyphrases
- audio visual
- speaker identification
- real time
- accurate localization
- localization method
- audio visual speech recognition
- multimedia
- motion model
- prosodic features
- localization algorithm
- automatic transcription
- audio stream
- location estimation
- visual data
- particle filtering
- particle filter
- visual information
- position information
- kalman filter
- mobile robot localization
- acoustic features
- multi stream
- visual tracking
- optical flow
- object tracking
- image sequences
- video surveillance
- pose estimation
- robust tracking
- motion tracking
- speech recognition