{
  "id": 10338682,
  "title": "Acoustic-to-Text KV Compression for Full-Duplex Speech Models",
  "url": "https://urgent.news/2026/09/25/acoustic-to-text-kv-compression-for-full-duplex-speech-models",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-25T13:04:09.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.31224v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Full-duplex speech language models continuously accumulate acoustic key-value (KV) states, making long-running interactions memory-intensive. During listening, the model can finish processing an audio unit before the next arrives; we term the remaining interval listening-time slack. We propose acoustic-to-text KV compression, which introduces a transcription side channel to convert incoming…",
  "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."
}