Search Results for author:
Found 5 papers, 1 papers with code
Joint Selective State Space Model and Detrending for Robust Time Series Anomaly Detection
Deep learning-based sequence models are extensively employed in Time Series Anomaly Detection (TSAD) tasks due to their effective sequential modeling capabilities.
StyleGAN3: Generative Networks for Improving the Equivariance of Translation and Rotation
StyleGAN can use style to affect facial posture and identity features, and noise to affect hair, wrinkles, skin color and other details.
MSS-PAE: Saving Autoencoder-based Outlier Detection from Unexpected Reconstruction
Experiments on 32 real-world OD datasets proved the effectiveness of the proposed methods.
Scaling sparsemax based channel selection for speech recognition with ad-hoc microphone arrays
Because Sparsemax punishes the weights of many channels to zero harshly, we propose Scaling Sparsemax which punishes the channels mildly by setting the weights of very noisy channels to zero only.
Libri-adhoc40: A dataset collected from synchronized ad-hoc microphone arrays
We trained several multi-device speech recognition systems on both the Libri-adhoc40 dataset and a simulated dataset.
