{
  "id": 5472086,
  "title": "Masked Autoregressive Speech Enhancement with Continuous Neural Audio Codec Representations",
  "url": "https://urgent.news/2026/09/03/masked-autoregressive-speech-enhancement-with-continuous-neural-audio",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-03T14:45:42.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.03940v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Most previous work on speech enhancement (SE) based on masked generative modeling relied on discrete token representations of audio signals, obtained using neural audio codecs (NACs). However, a recent study has shown that continuous latent representations of NACs can be advantageous for SE in terms of speech quality and intelligibility. In this work, we propose masked autoregressive SE (MARSE),…",
  "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."
}