Login / Signup
MRSLN: A Multimodal Residual Speaker-LSTM Network to alleviate the over-smoothing issue for Emotion Recognition in Conversation.
Nannan Lu
Zhen Tan
Jiansheng Qian
Published in:
Neurocomputing (2024)
Keyphrases
</>
emotion recognition
audio visual
speaker verification
multi modal
emotional speech
multi stream
visual information
human computer interaction
recurrent neural networks
natural language
speech recognition
sentiment analysis
visual data
facial expressions
multimedia
machine learning
text classification
low level