A CRNN with mixup and score-level fusion of four sub-spectrograms reaches 81.9% accuracy on ESC-50, a 9.1 percentage point gain over a plain CNN baseline.
Environmental sound recog- nition with time–frequency audio features,
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
-
Sub-Spectrogram Segmentation for Environmental Sound Classification via Convolutional Recurrent Neural Network and Score Level Fusion
A CRNN with mixup and score-level fusion of four sub-spectrograms reaches 81.9% accuracy on ESC-50, a 9.1 percentage point gain over a plain CNN baseline.