Metraipolis › archive › dc_9863e025e116

Beyond Model Size: Redesigning LiSenNet for embedded speech enhancement — arXiv:2609.29866

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.29866
License (as archived)
CC0-1.0
Archived
2026-10-08T05:26:37.718Z
SHA-256 of the archived text
25f922d8fa57238420a7ee236a15365662b5f51570c3519d6ff362bb38a93209
Stable URL of this page
https://metraipolis.com/documento/dc_9863e025e116

How to cite

Beyond Model Size: Redesigning LiSenNet for embedded speech enhancement — arXiv:2609.29866 — arXiv (en), https://arxiv.org/abs/2609.29866 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9863e025e116 (Metraipolis archive dc_9863e025e116, sha256 25f922d8fa57238420a7ee236a15365662b5f51570c3519d6ff362bb38a93209)
BibTeX
@misc{dc9863e025e116,
  title = {Beyond Model Size: Redesigning LiSenNet for embedded speech enhancement — arXiv:2609.29866},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29866},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9863e025e116; sha256 25f922d8fa57238420a7ee236a15365662b5f51570c3519d6ff362bb38a93209},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29866. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deploying real-time speech enhancement on resource-constrained devices requires meeting strict latency, memory, and energy constraints. Microcontroller NPUs can accelerate neural inference under these constraints, but only through a restricted set of operators in static, integer-quantized graphs. Recent speech-enhancement networks have reduced parameter counts and MACs to levels nominally suitable for microcontrollers, but their operators and execution patterns often remain incompatible with restricted NPUs. We address this gap by redesigning LiSenNet, a 37k parameter sub-band dual-path model, for the STM32N6570-DK Neural-ART accelerator. We replace its recurrent bottleneck with convolutional frequency and temporal mixers, reformulate unsupported operations as static int8-compatible primitives, and use bounded decoder activations to preserve quality after quantization. On VoiceBank-DEMAND, the final NPU-compatible model matches or exceeds the recurrent LiSenNet baseline, reaching PESQ 3.08 versus 3.01 in FP32 and 3.01 versus 2.93 in int8. Deployed on a microcontroller, it processes each 16 ms input hop in 4.83 ms, corresponding to a real-time factor of 0.30. Stateless receptive-field recomputation is an order of magnitude slower at the same frame rate despite higher accelerator utilization. These results show that parameter count and operator compatibility, quantization range, and persistent streaming state must be co-designed to achieve efficient real-time speech enhancement on restricted NPUs.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.LG).
Categorie arXiv: Audio and Speech Processing (eess.AS) ; Machine Learning (cs.LG); Sound (cs.SD).
Pagina del lavoro: https://arxiv.org/abs/2609.29866 — 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 2026-10-08T04:50:39.695Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).