Already It Was Hard to Tell Who's Speaking Over There, and Now Face Masks! Can Binaural Audio Help Remote Participation in Hybrid Meetings?
Loïc RossetHamed S. AlaviSailin ZhongDenis LalannePublished in: CHI Extended Abstracts (2021)
Keyphrases
- audio visual
- automatic transcription
- multimodal fusion
- multimedia
- signal processing
- face images
- visual information
- human faces
- face to face meetings
- sound source
- recognition algorithm
- facial images
- facial features
- computer vision
- multi modal
- edge detection
- hidden markov models
- remote access
- image sequences
- image processing
- decision making