Sub-band CNN applies distinct kernels per frequency sub-band to reduce computation 39.7-49.3% versus full-band CNN on Speech Commands dataset while maintaining accuracy.
We compare the pro- posed sub-band CNNs to full band CNNs and another weight sharing approach on two spoken term classification tasks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Sub-band Convolutional Neural Networks for Small-footprint Spoken Term Classification
Sub-band CNN applies distinct kernels per frequency sub-band to reduce computation 39.7-49.3% versus full-band CNN on Speech Commands dataset while maintaining accuracy.