Emotion Recognition With Multimodal Transformer Fusion Framework Based on Acoustic and Lexical Information.
Lili GuoLongbiao WangJianwu DangYahui FuJiaxing LiuShifei DingPublished in: IEEE Multim. (2022)
Keyphrases
- fusion framework
- lexical information
- emotion recognition
- emotional speech
- audio visual
- language processing
- fusion process
- multi modal
- fuzzy logic
- combining multiple
- human computer interaction
- part of speech
- facial expressions
- visual information
- sentiment analysis
- wordnet
- information fusion
- word sense disambiguation
- visual data
- multimedia
- semantic roles
- emotional state
- semantic similarity
- parse tree
- machine translation
- natural language processing
- natural language
- face recognition