DCCRN, a 1.38M-parameter hybrid of dilated DenseNet and GRU with a cross-component skip, reports consistent time-domain speech enhancement gains over single-stage baselines on TIMIT mixtures.
Suppression of acoustic noise in speech using spec- tral subtraction,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Dual-Staged Context Aggregation Method Towards Efficient End-To-End Speech Enhancement
DCCRN, a 1.38M-parameter hybrid of dilated DenseNet and GRU with a cross-component skip, reports consistent time-domain speech enhancement gains over single-stage baselines on TIMIT mixtures.