{
  "id": 8816292,
  "title": "Listen Before You Speak: Response Planning from Listener Facial Reactions for Conversational Speech Generation",
  "url": "https://urgent.news/2026/09/18/listen-before-you-speak-response-planning-from-listener-facial",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-18T12:18:16.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.21683v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Conversational speech depends on dialogue context and the listener's immediately preceding behavior. We propose ReACT-TTS, a two-stage framework that uses a one-second pre-response listener facial sequence to plan the next utterance's emotion and prosody before speech realization. On a strict dyadic MELD protocol, Temporal conditioning yields higher mean macro-F1 and VAD concordance than…",
  "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."
}