Jaesong Lee
Jaesong Lee
Verified email at - Homepage
Cited by
Cited by
Intermediate loss regularization for ctc-based speech recognition
J Lee, S Watanabe
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
Interactive visualization and manipulation of attention-based neural machine translation
J Lee, JH Shin, JS Kim
Proceedings of the 2017 Conference on Empirical Methods in Natural Language …, 2017
Point-based value iteration for constrained POMDPs
D Kim, J Lee, KE Kim, P Poupart
IJCAI 11, 1968-1974, 2011
A comparative study on non-autoregressive modelings for speech-to-text generation
Y Higuchi, N Chen, Y Fujita, H Inaguma, T Komatsu, J Lee, J Nozaki, ...
2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 47-54, 2021
Naver machine translation system for wat 2015
HG Lee, JS Lee, JS Kim, CK Lee
Proceedings of the 2nd Workshop on Asian Translation (WAT2015), 69-73, 2015
papago: A machine translation service with word sense disambiguation and currency conversion
HG Lee, JS Kim, JH Shin, J Lee, YX Quan, YS Jeong
Proceedings of COLING 2016, the 26th International Conference on …, 2016
A POMDP framework for dynamic task allocation and reconnaissance of multiple unmanned aerial vehicles
D Kim, J Lee, J Choi, KE Kim
Journal of KIISE: Software and Applications 39 (6), 453-463, 2012
Layer pruning on demand with intermediate CTC
J Lee, J Kang, S Watanabe
arXiv preprint arXiv:2106.09216, 2021
Memory-efficient training of RNN-Transducer with sampled softmax
J Lee, L Lee, S Watanabe
arXiv preprint arXiv:2203.16868, 2022
Large-scale learning of generalised representations for speaker recognition
J Jung, HS Heo, BJ Lee, J Lee, H Shim, Y Kwon, JS Chung, S Watanabe
arXiv preprint arXiv:2210.10985, 2022
Better Intermediates Improve CTC Inference
T Komatsu, Y Fujita, J Lee, L Lee, S Watanabe, Y Kida
arXiv preprint arXiv:2204.00176, 2022
I3D: Transformer architectures with input-dependent dynamic depth for speech recognition
Y Peng, J Lee, S Watanabe
ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023
The system can't perform the operation now. Try again later.
Articles 1–12