no code implementations • ICASSP 2022 • Taesoo Kim, Jiho Chang, Jong Hwan Ko
In this paper, we propose adversarial domain adaptive VAD (ADA-VAD), which is a deep neural network (DNN) based VAD method highly robust to audio samples with various noise types and low SNRs.
Ranked #4 on Activity Detection on AVA-Speech (ROC-AUC metric)