A learnable residual speech-to-spike encoder jointly trained with an R-LIF SNN achieves up to 94.97% accuracy on GSC-v2 with a 35k-parameter model and supports DFA credit assignment at 91.5%.
Available: https://www.frontiersin.org/journals/ neuroscience/articles/10.3389/fnins.2020.00662
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Adaptive Speech-to-Spike Encoding for Spiking Neural Networks
A learnable residual speech-to-spike encoder jointly trained with an R-LIF SNN achieves up to 94.97% accuracy on GSC-v2 with a 35k-parameter model and supports DFA credit assignment at 91.5%.