From prediction error to sparse events: Biologically inspired signed-dyadic coding for Mandarin keyword spotting
This paper proposes Predictive Signed-Dyadic Coding (PG) for efficient continuous spiking keyword spotting.
PG introduces a novel approach to efficient continuous spiking keyword spotting by retaining predictable input locally and responding selectively to deviations.
Before reading this…
Applications
- →Keyword spotting
- →Low-power continuous speech processing
- →Event-based sensory systems
To understand this paper, make sure you know these concepts first:
- Predictive processingfind papers →
- Sensory adaptationfind papers →
Abstract
More Like ThisIn 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.