no code implementations • 28 Mar 2023 • Jin Sob Kim, Hyun Joon Park, WooSeok Shin, Sung Won Han
Hence, the format enables the model to handle the polyphony problem, regardless of the number of sound overlaps.
1 code implementation • 16 Mar 2023 • Hyun Joon Park, Seok Woo Yang, Jin Sob Kim, WooSeok Shin, Sung Won Han
The existing methods do not simultaneously satisfy the above two aspects of VC, and their conversion outputs suffer from a trade-off problem between maintaining source contents and target characteristics.
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.
1 code implementation • 4 Mar 2022 • Hyun Joon Park, Byung Ha Kang, WooSeok Shin, Jin Sob Kim, Sung Won Han
In the field of speech enhancement, time domain methods have difficulties in achieving both high performance and efficiency.
Ranked #6 on Speech Enhancement on VoiceBank + DEMAND
1 code implementation • 14 Dec 2021 • Min Seok Lee, WooSeok Shin, Sung Won Han
Existing studies on salient object detection (SOD) focus on extracting distinct objects with edge information and aggregating multi-level features to improve SOD performance.
Ranked #1 on RGB Salient Object Detection on DUT-OMRON