A spike-driven speech-command model with global-local attention and curriculum time-step distillation reaches strong accuracy at 40 time steps while cutting theoretical energy use by 54.8%.
N.; Fan, A.; Auli, M.; and Grangier, D
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Efficient Speech Command Recognition Leveraging Spiking Neural Network and Curriculum Learning-based Knowledge Distillation
A spike-driven speech-command model with global-local attention and curriculum time-step distillation reaches strong accuracy at 40 time steps while cutting theoretical energy use by 54.8%.