{
  "id": 8148346,
  "title": "Reading Emotions in the Token Space: Discriminative Adaptation of SpeechLLMs for Emotion Recognition",
  "url": "https://urgent.news/2026/09/17/reading-emotions-in-the-token-space-discriminative-adaptation-of",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-17T11:38:44.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.20081v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "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 through a classification head, producing a label in one forward pass without…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}