2 papers
cs.LG2023
Pseudo-label Correction for Instance-dependent Noise Using Teacher-student Framework
Eugene Kim
The high capacity of deep learning models to learn complex patterns poses a significant challenge when confronted with label noise. The inability to differentiate clean and noisy l…
cs.CL2021
Query-by-Example Keyword Spotting system using Multi-head Attention and Softtriple Loss
Jinmiao Huang, Waseem Gharbieh, Han Suk Shim +1
This paper proposes a neural network architecture for tackling the query-by-example user-defined keyword spotting task. A multi-head attention module is added on top of a multi-lay…