Metraipolis › archive › dc_df947ddf0bfe

MiDashengLM-Gen: Unified Audio Scene Generation via LLM-Driven Autoregressive Flow Matching — arXiv:2608.11804

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.11804
License (as archived)
CC0-1.0
Archived
2026-10-19T06:07:11.068Z
SHA-256 of the archived text
0736f63d8554775d20e3c12fb4c4ecc3499fc9efa177306b0ffd84adae6d680e
Stable URL of this page
https://metraipolis.com/documento/dc_df947ddf0bfe

How to cite

MiDashengLM-Gen: Unified Audio Scene Generation via LLM-Driven Autoregressive Flow Matching — arXiv:2608.11804 — arXiv (en), https://arxiv.org/abs/2608.11804 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_df947ddf0bfe (Metraipolis archive dc_df947ddf0bfe, sha256 0736f63d8554775d20e3c12fb4c4ecc3499fc9efa177306b0ffd84adae6d680e)
BibTeX
@misc{dcdf947ddf0bfe,
  title = {MiDashengLM-Gen: Unified Audio Scene Generation via LLM-Driven Autoregressive Flow Matching — arXiv:2608.11804},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.11804},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_df947ddf0bfe; sha256 0736f63d8554775d20e3c12fb4c4ecc3499fc9efa177306b0ffd84adae6d680e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11804. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generating coherent audio scenes that simultaneously blend speech, music, and sound effects remains a significant challenge. Current approaches typically rely on a disjointed pipeline where a frozen, decoupled text encoder feeds a separate audio decoder, limiting cross-modal optimization and leading to poor speech intelligibility. To overcome these limitations, we introduce MiDashengLM-Gen, an end-to-end framework that couples a pre-trained Large Language Model (LLM) with per-token conditional flow matching for autoregressive, variable-length mixed-audio scene generation. MiDashengLM-Gen represents a first approach for general text-to-audio generation with one end-to-end trained model. Empirical evaluations demonstrate that MiDashengLM-Gen drastically improves speech intelligibility over existing unified models. On the Seed-TTS benchmark, English Word Error Rate (WER) drops from 12.15% to 2.79%, approaching the performance of dedicated Text-to-Speech (TTS) systems (1.24%). Furthermore, the framework extends effectively to multilingual settings, yielding highly competitive multilingual WERs compared to existing baselines. Lastly, the model maintains competitive mixed-audio generation quality on the MECAT benchmark. Code and checkpoints are available at this https URL and this https URL , and the demo page is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in eess.AS).
Categorie arXiv: Audio and Speech Processing (eess.AS) ; Sound (cs.SD).
Pagina del lavoro: https://arxiv.org/abs/2608.11804 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T05:56:37.843Z dalla pagina https://arxiv.org/catchup/eess.AS/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).