GitHub

Sinc convolution for a finite interval

Sinc convolution combined with the single-exponential (SE) transformation [2] Sinc convolution combined with the double-exponential (DE) transformation [1] The name of the program denotes the example ...
IEEE

Interpretability and Optimisation of Convolutional Neural Networks Based on Sinc-Convolution

Abstract: Interpretability often seeks domain-specific facts, which is understandable to human, from deep-learning (DL) or other machine-learning (ML) models of black-box nature. This is particularly ...
IEEE

What Do Neural Networks Listen to? Exploring the Crucial Bands in Speech Enhancement Using ...

Abstract: This study introduces a reformed Sinc-convolution (Sincconv) framework tailored for the encoder component of deep networks for speech enhancement (SE). The reformed Sinc-conv, based on ...
GitHub

Soft-Isomorphic Neighborhood-Contextualized Graph Convolution Network (SINC-GCN)

SINC-GCN, as an instance of the neighborhood-contextualized message-passing (NCMP) GNN variant, integrates contextualized messages (i.e., anisotropic and dynamic messages) and ...