Reading Emotions in the Token Space: Discriminative Adaptation of SpeechLLMs for Emotion Recognition
SpeechLLMs have shown strong potential for emotion recognition, yet they read the predicted emotion off a generative decoder not suited for classification: it can emit labels outside the target set and favors frequent classes. We propose a discriminative adaptation that reads the final prompt token's hidden state throu...
Hasindri Watawana, Sergio Gastón Burdisso, Esaú Villatoro-Tello et al.
· 0 citations