Decomposed Temporal Dynamic CNN: Efficient Time-Adaptive Network for Text-Independent Speaker Verification Explained with Speaker Activation Map

29 March 2022

Papers citing "Decomposed Temporal Dynamic CNN: Efficient Time-Adaptive Network for Text-Independent Speaker Verification Explained with Speaker Activation Map"

3 / 3 papers shown

Title
Data Augmentation and Squeeze-and-Excitation Network on Multiple Dimension for Sound Event Localization and Detection in Real Scenes Byeongil Ko Hyeonuk Nam Seong-Hu Kim D. Min Seung-Deok Choi Yong-Hwa Park 26 7 0 24 Jun 2022
Frequency and Multi-Scale Selective Kernel Attention for Speaker Verification Sung Hwan Mun Jee-weon Jung Min Hyun Han N. Kim 44 21 0 03 Apr 2022
VoxCeleb2: Deep Speaker Recognition Joon Son Chung Arsha Nagrani Andrew Zisserman 216 2,233 0 14 Jun 2018