Metraipolis › archive › dc_edcf567fdef0
From prediction error to sparse events: Biologically inspired signed-dyadic coding for Mandarin keyword spotting — arXiv:2610.41381
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41381
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-02T04:45:17.747Z
- SHA-256 of the archived text
ecbdeebd2bc2dbd2e7eac673f674221e05473242be8a30c59428d2ceb6138cfd- Stable URL of this page
https://metraipolis.com/documento/dc_edcf567fdef0
How to cite
From prediction error to sparse events: Biologically inspired signed-dyadic coding for Mandarin keyword spotting — arXiv:2610.41381 — arXiv (en), https://arxiv.org/abs/2610.41381 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_edcf567fdef0 (Metraipolis archive dc_edcf567fdef0, sha256 ecbdeebd2bc2dbd2e7eac673f674221e05473242be8a30c59428d2ceb6138cfd)
BibTeX
@misc{dcedcf567fdef0,
title = {From prediction error to sparse events: Biologically inspired signed-dyadic coding for Mandarin keyword spotting — arXiv:2610.41381},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41381},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_edcf567fdef0; sha256 ecbdeebd2bc2dbd2e7eac673f674221e05473242be8a30c59428d2ceb6138cfd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41381. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In continuous spiking keyword spotting, temporally correlated acoustic frames can repeatedly trigger memory access and neural computation at a dense input interface, even when hidden activity is sparse. Predictive processing and sensory adaptation suggest retaining predictable input locally and responding selectively to deviations. Inspired by this mechanism, we propose Predictive Signed-Dyadic Coding (PG). PG maintains a local prediction for each input channel and transmits an event only when the residual exceeds a learned threshold. Each event carries a sign and a finite power-of-two magnitude, and the receiver reconstructs it with fixed-point shifts and additions. In Mandarin keyword spotting, INPUT-PG reaches 90.00% accuracy while reducing mean SRAM reads by 33.87% and inference cycles by 32.77%. PG provides a hardware interface for research on low-power continuous speech processing and event-based sensory systems. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Sound (cs.SD) ; Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2610.41381 — 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 2026-11-02T04:42:12.463Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).