Metraipolis › archive › dc_6ddf269ab407

A Lightweight Hybrid Framework for Acoustic Echo Cancellation and Suppression via Constrained Recursive Training — arXiv:2610.09655

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.09655
License (as archived)
CC0-1.0
Archived
2026-10-08T14:17:26.668Z
SHA-256 of the archived text
261cf449ce27ea7383cc8fcf1e5f044e63348c4548592f5b2c8fdcc46a059b3a
Stable URL of this page
https://metraipolis.com/documento/dc_6ddf269ab407

How to cite

A Lightweight Hybrid Framework for Acoustic Echo Cancellation and Suppression via Constrained Recursive Training — arXiv:2610.09655 — arXiv (en), https://arxiv.org/abs/2610.09655 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6ddf269ab407 (Metraipolis archive dc_6ddf269ab407, sha256 261cf449ce27ea7383cc8fcf1e5f044e63348c4548592f5b2c8fdcc46a059b3a)
BibTeX
@misc{dc6ddf269ab407,
  title = {A Lightweight Hybrid Framework for Acoustic Echo Cancellation and Suppression via Constrained Recursive Training — arXiv:2610.09655},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09655},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6ddf269ab407; sha256 261cf449ce27ea7383cc8fcf1e5f044e63348c4548592f5b2c8fdcc46a059b3a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09655. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We propose a hybrid framework that combines deep learning with adaptive filtering for acoustic echo cancellation (AEC) and suppression. It integrates a multi-output neural network to jointly update filter parameters and perform post-processing. A learnable variant of the normalized least mean squares (NLMS) filter is introduced, incorporating a variable step size and a variable transition factor that are recursively updated for dynamic adaptation. In addition, an enhanced near-end speech estimate is generated from the filter output to suppress the residual echoes. To ensure training stability, we propose a constrained recursive training strategy that aligns with the adaptive nature of the filter, where an upper-bound constraint is introduced on the filter output. For efficiency, the framework adopts a lightweight implementation with only 253 k parameters. Experimental results show that the framework outperforms the baselines in terms of both signal quality and speech intelligibility.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv eess.AS, nuovi lavori del giorno).
Categorie arXiv: Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2610.09655 — 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 2026-10-08T13:29:00.762Z dalla pagina https://arxiv.org/list/eess.AS/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).