Audio-Visual Speaker Diarization in the Framework of Multi-User Human-Robot Interaction.

Timothée Dhaussy Bassam Jabaian Fabrice Lefèvre Radu Horaud

Published in: ICASSP (2023)

Keyphrases

multi user
audio visual
human robot interaction
multi modal
virtual world
neural network
computer vision
probabilistic model
emotion recognition
image features
natural language processing
virtual environment
visual information