预测符号二元编码（PG）用于普通话关键词检测的类脑事件稀疏编码方法
From prediction error to sparse events: Biologically inspired signed-dyadic coding for Mandarin keyword spotting
AI 导读
研究者提出预测符号二元编码（Predictive Signed-Dyadic Coding，PG），借鉴预测加工与感官适应机制，仅在残差超过学习阈值时传输带符号和 2 的幂幅度的事件，接收端用定点移位与加法即可重建输入。
正文 · 原文
Abstract: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.
| Comments: | 14 pages, 4 figures |
| Subjects: | Sound (cs.SD); Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS) |
| Cite as: | arXiv:2610.41381 [cs.SD] |
| (or arXiv:2610.41381v1 [cs.SD] for this version) | |
| https://doi.org/10.48550/arXiv.2610.41381 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zijian Zhou [view email]
[v1]
Fri, 30 Oct 2026 07:46:45 UTC (166 KB)
来源：arXiv cs.AI · arxiv.org