Fusion of VGG-like 2D CNN, Light-CNN, and x-vector 1D CNN with self-attention pooling on 256-dim log Mel-spectrograms, trained on 4-fold splits and combined with multiple fusion strategies for DCASE2019 Task 1.
Attention-based models for text-dependent speaker verifi ca- tion,
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
-
Acoustic Scene Classification Using Fusion of Attentive Convolutional Neural Networks for DCASE2019 Challenge
Fusion of VGG-like 2D CNN, Light-CNN, and x-vector 1D CNN with self-attention pooling on 256-dim log Mel-spectrograms, trained on 4-fold splits and combined with multiple fusion strategies for DCASE2019 Task 1.