2 papers
cs.LG2025
Towards Efficient Few-shot Graph Neural Architecture Search via Partitioning Gradient Contribution
Wenhao Song, Xuan Wu, Bo Yang +6
To address the weight coupling problem, certain studies introduced few-shot Neural Architecture Search (NAS) methods, which partition the supernet into multiple sub-supernets. Howe…
eess.AS2020
Crossed-Time Delay Neural Network for Speaker Recognition
Liang Chen, Yanchun Liang, Xiaohu Shi +2
Time Delay Neural Network (TDNN) is a well-performing structure for DNN-based speaker recognition systems. In this paper we introduce a novel structure Crossed-Time Delay Neural Ne…