2 papers
cs.LG2021
Noisy student-teacher training for robust keyword spotting
Hyun-Jin Park, Pai Zhu, Ignacio Lopez Moreno +1
We propose self-training with noisy student-teacher approach for streaming keyword spotting, that can utilize large-scale unlabeled data and aggressive data augmentation. The propo…
cs.CL2020
Learning To Detect Keyword Parts And Whole By Smoothed Max Pooling
Hyun-Jin Park, Patrick Violette, Niranjan Subrahmanya
We propose smoothed max pooling loss and its application to keyword spotting systems. The proposed approach jointly trains an encoder (to detect keyword parts) and a decoder (to de…