Metraipolis › archive › dc_5e79fcdb382e

DiffVQE2: An Efficient Low-delay Diffusion Model for Acoustic Echo and Noise Control — arXiv:2609.31703

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.31703
License (as archived): CC0-1.0
Archived: 2026-10-08T01:37:13.161Z
SHA-256 of the archived text: c99ba08be573272665622a7fd4343af4b435cc1c98daa3038e9d45816d4b2d5e
Stable URL of this page: https://metraipolis.com/documento/dc_5e79fcdb382e

How to cite

DiffVQE2: An Efficient Low-delay Diffusion Model for Acoustic Echo and Noise Control — arXiv:2609.31703 — arXiv (en), https://arxiv.org/abs/2609.31703 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5e79fcdb382e (Metraipolis archive dc_5e79fcdb382e, sha256 c99ba08be573272665622a7fd4343af4b435cc1c98daa3038e9d45816d4b2d5e)

BibTeX

@misc{dc5e79fcdb382e,
  title = {DiffVQE2: An Efficient Low-delay Diffusion Model for Acoustic Echo and Noise Control — arXiv:2609.31703},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31703},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5e79fcdb382e; sha256 c99ba08be573272665622a7fd4343af4b435cc1c98daa3038e9d45816d4b2d5e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31703. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Hands-free communication devices and speakerphones are inherently affected by acoustic echo and background noise. To mitigate these impairments, end-to-end discriminatively trained neural networks have emerged as the best-performing approach in research and deployment. While recent advancements in generative methods have provided remarkable results for various speech enhancement tasks, diffusion-based acoustic echo control (AEC) research is still restricted to non-causal, utterance-level processing, thereby not widely applicable in practice. With this work, we are the first to propose low-delay (i.e., causal) diffusion-based joint AEC and noise control models DiffVQE2 / DiffVQE2-S, excelling the so-far state of the art DeepVQE / DeepVQE-S models in multiple objective metrics, and, most importantly, in subjective MOS, respectively. In addition, our models are less complex. Furthermore, we show that a limited lookahead applied to the efficient DiffVQE2-S model allows for an even higher performance. These results have been obtained on the ICASSP 2023 AEC Challenge blind test set. We claim the first streaming-capable, diffusion-based acoustic echo and noise control that excels state-of-the-art discriminative approaches.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in eess.AS).
Categorie arXiv: Audio and Speech Processing (eess.AS) ; Sound (cs.SD).
Pagina del lavoro: https://arxiv.org/abs/2609.31703 — 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 2026-10-08T01:11:22.046Z dalla pagina https://arxiv.org/catchup/eess.AS/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).