Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Jaesung Huh

VoxSRC 2021: The Third VoxCeleb Speaker Recognition Challenge

Jan 12, 2022
Andrew Brown, Jaesung Huh, Joon Son Chung, Arsha Nagrani, Andrew Zisserman

* arXiv admin note: substantial text overlap with arXiv:2012.06867 

  Access Paper or Ask Questions

With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition

Nov 01, 2021
Evangelos Kazakos, Jaesung Huh, Arsha Nagrani, Andrew Zisserman, Dima Damen

* Accepted at BMVC 2021 

  Access Paper or Ask Questions

VoxSRC 2020: The Second VoxCeleb Speaker Recognition Challenge

Dec 12, 2020
Arsha Nagrani, Joon Son Chung, Jaesung Huh, Andrew Brown, Ernesto Coto, Weidi Xie, Mitchell McLaren, Douglas A Reynolds, Andrew Zisserman

  Access Paper or Ask Questions

Augmentation adversarial training for unsupervised speaker recognition

Aug 09, 2020
Jaesung Huh, Hee Soo Heo, Jingu Kang, Shinji Watanabe, Joon Son Chung

  Access Paper or Ask Questions

Spot the conversation: speaker diarisation in the wild

Jul 02, 2020
Joon Son Chung, Jaesung Huh, Arsha Nagrani, Triantafyllos Afouras, Andrew Zisserman

* The dataset will be available for download from . The development set will be released in July 2020, and the test set will be released in October 2020 

  Access Paper or Ask Questions

Modeling Musical Onset Probabilities via Neural Distribution Learning

Feb 10, 2020
Jaesung Huh, Egil Martinsson, Adrian Kim, Jung-Woo Ha

* 2 pages, 2 figures, 2 tables 

  Access Paper or Ask Questions

Delving into VoxCeleb: environment invariant speaker recognition

Oct 24, 2019
Joon Son Chung, Jaesung Huh, Seongkyu Mun

  Access Paper or Ask Questions

Phase-aware Speech Enhancement with Deep Complex U-Net

Apr 02, 2019
Hyeong-Seok Choi, Jang-Hyun Kim, Jaesung Huh, Adrian Kim, Jung-Woo Ha, Kyogu Lee

* Significant error was found in data processing step, therefore will be retracted from International Conference on Learning Representations (ICLR) 2019. It is not recommended to read current version 

  Access Paper or Ask Questions