Seven continual learning methods are evaluated on a binary neural network keyword spotter, showing that new keywords can be added on-device with accuracy above 82 percent in the tested scenarios.
An in-vehicle keyword spotting system with multi-source fusion for vehicle applications,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Efficient Continual Learning in Keyword Spotting using Binary Neural Networks
Seven continual learning methods are evaluated on a binary neural network keyword spotter, showing that new keywords can be added on-device with accuracy above 82 percent in the tested scenarios.