Speaker-Centric Multimodal Fusion Networks for Emotion Recognition in Conversations.

Biyun Yao Wuzhen Shi

Published in: ICASSP (2024)

Keyphrases

audio visual
multimodal fusion
emotion recognition
speaker verification
multi modal
emotional speech
visual information
visual data
multimedia
human computer interaction
artificial intelligence
high level
image sequences
high dimensional
natural language processing
sentiment analysis