A custom convolutional speech enhancement network with a learned gating module skips individual channels at runtime, saving up to 29.6% of MACs on VoiceBank+DEMAND with a negligible PESQ drop.
Similarly, the test set includes 824 samples from two other speakers mixed with unseen noise at SNR between 17.5 dB and 2.5 dB
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
eess.AS 1years
2024 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Scalable Speech Enhancement with Dynamic Channel Pruning
A custom convolutional speech enhancement network with a learned gating module skips individual channels at runtime, saving up to 29.6% of MACs on VoiceBank+DEMAND with a negligible PESQ drop.