Emotion as a Distribution: Joint Valence-Arousal Probability Learning for Speaker-Independent Multimodal Emotion Recognition
This text+speech system, alongside its categorical decision, emits a $9\times9$ probability matrix over the Valence-Arousal plane, trained with a two-dimensional Gaussian soft target under a Kullback-Leibler/cross-entropy objective, aimed at counseling support.
Ting Lin, Wen-Ren Yang, Kuan-Wei Chen
· 0 citations