1 code implementation • ICML 2023 • WooSeok Shin, Byung Hoon Lee, Jin Sob Kim, Hyun Joon Park, Sung Won Han
In speech enhancement, MetricGAN-based approaches reduce the discrepancy between the $L_p$ loss and evaluation metrics by utilizing a non-differentiable evaluation metric as the objective function.
Ranked #6 on Speech Enhancement on VoiceBank + DEMAND
no code implementations • 22 Aug 2022 • WooSeok Shin, Hyun Joon Park, Jin Sob Kim, Byung Hoon Lee, Sung Won Han
In this study, we propose multi-view attention transfer (MV-AT), a feature-based distillation, to obtain efficient speech enhancement models in the time domain.
Ranked #13 on Speech Enhancement on VoiceBank + DEMAND