no code implementations • 3 Jun 2021 • Hyun-Jin Park, Pai Zhu, Ignacio Lopez Moreno, Niranjan Subrahmanya
We propose self-training with noisy student-teacher approach for streaming keyword spotting, that can utilize large-scale unlabeled data and aggressive data augmentation.
no code implementations • 25 Jan 2020 • Hyun-Jin Park, Patrick Violette, Niranjan Subrahmanya
We propose smoothed max pooling loss and its application to keyword spotting systems.