Metraipolis › archive › dc_b17c3adbed0e

UNITE-AUDIO: Joint Learning of Continuous Tokenization and Latent Flow Matching for Text-to-Audio Generation — arXiv:2609.28206

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.28206
License (as archived)
CC0-1.0
Archived
2026-10-08T13:39:36.847Z
SHA-256 of the archived text
0f5772c666ff784bb0c93204d4f9654702a6abd62b616d5d97db8bfd5aadfc66
Stable URL of this page
https://metraipolis.com/documento/dc_b17c3adbed0e

How to cite

UNITE-AUDIO: Joint Learning of Continuous Tokenization and Latent Flow Matching for Text-to-Audio Generation — arXiv:2609.28206 — arXiv (en), https://arxiv.org/abs/2609.28206 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b17c3adbed0e (Metraipolis archive dc_b17c3adbed0e, sha256 0f5772c666ff784bb0c93204d4f9654702a6abd62b616d5d97db8bfd5aadfc66)
BibTeX
@misc{dcb17c3adbed0e,
  title = {UNITE-AUDIO: Joint Learning of Continuous Tokenization and Latent Flow Matching for Text-to-Audio Generation — arXiv:2609.28206},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.28206},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b17c3adbed0e; sha256 0f5772c666ff784bb0c93204d4f9654702a6abd62b616d5d97db8bfd5aadfc66},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28206. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Text-to-audio (TTA) generation aims to synthesize realistic audio that faithfully reflects natural-language descriptions. Most TTA systems adopt a two-stage latent paradigm: an audio tokenizer is optimized for reconstruction and then frozen, after which a generative model is trained in the resulting latent space. However, reconstruction-oriented representations may be suboptimal for generation, motivating joint representation and generative learning. To this end, we introduce Unite-Audio, to our knowledge, is the first to jointly learn continuous audio representations and latent flow matching for TTA. By coupling reconstruction with self-supervised generative prediction, Unite-Audio allows the generative objective to directly shape the latent space rather than treating it as a fixed intermediate representation. We further employ Flow-GRPO post-training to improve text-conditioned generation. Experiments show competitive TTA performance with a compact latent flow model, while ablation studies confirm the benefit of jointly learning the audio representation and generative model. Audio samples are available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in eess.AS).
Categorie arXiv: Audio and Speech Processing (eess.AS) ; Sound (cs.SD).
Pagina del lavoro: https://arxiv.org/abs/2609.28206 — 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 2026-10-08T13:17:01.857Z dalla pagina https://arxiv.org/catchup/eess.AS/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).