Metraipolis › archive › dc_69a3e2f433d9
RT-SEMamba: Real-Time Speech Enhancement Mamba via Progressive Knowledge Distillation — arXiv:2608.12099
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.12099
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T05:31:01.553Z
- SHA-256 of the archived text
c2850930d6f65aab4829ee0116d4bf9e1dca77f016f7eb846fb495ee6a10b0cc- Stable URL of this page
https://metraipolis.com/documento/dc_69a3e2f433d9
How to cite
RT-SEMamba: Real-Time Speech Enhancement Mamba via Progressive Knowledge Distillation — arXiv:2608.12099 — arXiv (en), https://arxiv.org/abs/2608.12099 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_69a3e2f433d9 (Metraipolis archive dc_69a3e2f433d9, sha256 c2850930d6f65aab4829ee0116d4bf9e1dca77f016f7eb846fb495ee6a10b0cc)
BibTeX
@misc{dc69a3e2f433d9,
title = {RT-SEMamba: Real-Time Speech Enhancement Mamba via Progressive Knowledge Distillation — arXiv:2608.12099},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.12099},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_69a3e2f433d9; sha256 c2850930d6f65aab4829ee0116d4bf9e1dca77f016f7eb846fb495ee6a10b0cc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12099. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We present RT-SEMamba, a fully causal speech enhancement (SE) model built upon causal time-frequency Mamba blocks. Unlike Transformer-based architectures that rely on a growing key-value cache, Mamba propagates a fixed-size recurrent state per layer, enabling memory- and bandwidth-efficient long-form inference. We further introduce a progressive knowledge distillation (KD) strategy that compresses an 8-layer teacher into a shallow 1-layer student by jointly distilling complex spectral outputs and intermediate representations. On Voicebank-DEMAND, the 8-layer RT-SEMamba achieves 3.32 PESQ with a 25 ms algorithmic latency constraint, and the distilled 1-layer student improves over a naive 1-layer baseline from 3.06 to 3.18 PESQ while preserving the same steady-state RTF, delivering a 2.64x speedup over the teacher. These results demonstrate that state-space models with progressive KD provide a competitive quality-latency trade-off for real-time SE. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.CL). Categorie arXiv: Sound (cs.SD) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2608.12099 — 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 2026-10-19T05:15:39.260Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).