Подписаться
Yoohwan Kwon
Yoohwan Kwon
Naver Corporation
Подтвержден адрес электронной почты в домене navercorp.com - Главная страница
Название
Процитировано
Процитировано
Год
The ins and outs of speaker recognition: lessons from VoxSRC 2020
Y Kwon, HS Heo, BJ Lee, JS Chung
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
732021
Look who's talking: Active speaker detection in the wild
YJ Kim, HS Heo, S Choe, SW Chung, Y Kwon, BJ Lee, Y Kwon, JS Chung
arXiv preprint arXiv:2108.07640, 2021
302021
Intra-class variation reduction of speaker representation in disentanglement framework
Y Kwon, SW Chung, HG Kang
INTERSPEECH, 2020, 2020
232020
Mole: Mixture of language experts for multi-lingual automatic speech recognition
Y Kwon, SW Chung
ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023
202023
Cross attentive pooling for speaker verification
SM Kye, Y Kwon, JS Chung
2021 IEEE spoken language technology workshop (SLT), 294-300, 2021
162021
Disentangled representations for arabic dialect identification based on supervised clustering with triplet loss
Z Alhakeem, Y Kwon, HG Kang
2021 29th European Signal Processing Conference (EUSIPCO), 526-530, 2021
42021
Learning in your voice: Non-parallel voice conversion based on speaker consistency loss
Y Kwon, SW Chung, HS Heo, HG Kang
arXiv preprint arXiv:2011.02168, 2020
12020
A study on speech disentanglement framework based on adversarial learning for speaker recognition
Y Kwon, SW Chung, HG Kang
The Journal of the Acoustical Society of Korea 39 (5), 447-453, 2020
2020
В данный момент система не может выполнить эту операцию. Повторите попытку позднее.
Статьи 1–8