Metraipolis › archive › dc_415e73be044f

Training DeepFilterNet with Accurate Room Acoustic Simulations Improves Single-Channel Speech Enhancement — arXiv:2608.20971

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.20971
License (as archived): CC0-1.0
Archived: 2026-10-18T10:31:30.493Z
SHA-256 of the archived text: 78336771087f8a1a9a403bdc4e4581958feaa29d09832fd57fdf6833e004c8ad
Stable URL of this page: https://metraipolis.com/documento/dc_415e73be044f

How to cite

Training DeepFilterNet with Accurate Room Acoustic Simulations Improves Single-Channel Speech Enhancement — arXiv:2608.20971 — arXiv (en), https://arxiv.org/abs/2608.20971 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_415e73be044f (Metraipolis archive dc_415e73be044f, sha256 78336771087f8a1a9a403bdc4e4581958feaa29d09832fd57fdf6833e004c8ad)

BibTeX

@misc{dc415e73be044f,
  title = {Training DeepFilterNet with Accurate Room Acoustic Simulations Improves Single-Channel Speech Enhancement — arXiv:2608.20971},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.20971},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_415e73be044f; sha256 78336771087f8a1a9a403bdc4e4581958feaa29d09832fd57fdf6833e004c8ad},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20971. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We investigate how the realism of synthetic room impulse response (RIR) datasets affects the training of DeepFilterNet3 for single-channel speech enhancement. We compare a DNS4 image-source-method (ISM) RIR dataset with a higher-acoustic-fidelity dataset generated using hybrid wave-based and geometrical acoustics simulation. Rather than isolating individual simulation factors, we compare complete RIR generation pipelines while keeping the enhancement model unchanged. Models are evaluated on unseen measured RIRs using objective speech enhancement metrics and downstream automatic speech recognition (ASR). Training with the higher-fidelity dataset consistently yields modest improvements in objective metrics and substantially lower ASR word error rates than the ISM dataset. Although the experiments do not attribute these gains to individual modelling components, they show that increasing the overall realism of synthetic acoustic training data improves the generalization of DeepFilterNet3 to unseen measured environments.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-24 in cs.LG).
Categorie arXiv: Audio and Speech Processing (eess.AS) ; Machine Learning (cs.LG); Computational Physics (physics.comp-ph).
Pagina del lavoro: https://arxiv.org/abs/2608.20971 — 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 2026-10-18T10:27:55.998Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).