GLMB 3D Speaker Tracking with Video-Assisted Multi-Channel Audio Optimization Functions.
Xinyuan QianZexu PanQiquan ZhangKainan ChenShoufeng LinPublished in: ICASSP (2024)
Keyphrases
- multi channel
- multimedia
- audio video
- audio stream
- audio visual
- visual data
- digital video
- video data
- video streams
- video scene
- single channel
- audio files
- multimedia information
- anti aliasing
- video sequences
- prosodic features
- automatic transcription
- video frames
- video files
- signal processing
- visual information
- video content
- video surveillance
- particle filter
- visual speech
- soccer video
- channel assignment
- data broadcast
- multimedia data
- acoustic features
- speaker verification
- speaker identification
- broadcast news
- audio features
- video clips
- feature vectors