Metraipolis › archive › dc_41b36f8b980c
StuPASE: Towards Low-Hallucination Studio-Quality Generative Speech Enhancement — arXiv:2603.09234
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2603.09234
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T12:17:22.045Z
- SHA-256 of the archived text
1ead4caffad269afeb409072e74c03959cfc462fdbeac73c7ccd4a288421dc54- Stable URL of this page
https://metraipolis.com/documento/dc_41b36f8b980c
How to cite
StuPASE: Towards Low-Hallucination Studio-Quality Generative Speech Enhancement — arXiv:2603.09234 — arXiv (en), https://arxiv.org/abs/2603.09234 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_41b36f8b980c (Metraipolis archive dc_41b36f8b980c, sha256 1ead4caffad269afeb409072e74c03959cfc462fdbeac73c7ccd4a288421dc54)
BibTeX
@misc{dc41b36f8b980c,
title = {StuPASE: Towards Low-Hallucination Studio-Quality Generative Speech Enhancement — arXiv:2603.09234},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2603.09234},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_41b36f8b980c; sha256 1ead4caffad269afeb409072e74c03959cfc462fdbeac73c7ccd4a288421dc54},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2603.09234. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Achieving high perceptual quality without hallucination remains a challenge in generative speech enhancement (SE). A representative approach, PASE, is robust to hallucination but has limited perceptual quality under adverse conditions. We propose StuPASE, built upon PASE to achieve studio-level quality while retaining its low-hallucination property. First, we show that finetuning PASE with dry targets rather than targets containing simulated early reflections substantially improves dereverberation. Second, to address performance limitations under strong additive noise, we replace the GAN-based generative module in PASE with a flow-matching module, enabling studio-quality generation even under highly challenging conditions. Experiments demonstrate that StuPASE consistently produces perceptually high-quality speech while maintaining low hallucination, outperforming state-of-the-art SE methods. Audio demos are available at: this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI). Categorie arXiv: Audio and Speech Processing (eess.AS) ; Artificial Intelligence (cs.AI); Sound (cs.SD). Pagina del lavoro: https://arxiv.org/abs/2603.09234 — 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 2026-10-31T12:05:52.882Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).