| Softflow: Probabilistic framework for normalizing flow on manifolds H Kim, H Lee, WH Kang, JY Lee, NS Kim Advances in Neural Information Processing Systems 33, 16388-16397, 2020 | 104 | 2020 |
| A multi-resolution approach to GAN-based speech enhancement HY Kim, JW Yoon, SJ Cheon, WH Kang, NS Kim Applied Sciences 11 (2), 721, 2021 | 25 | 2021 |
| Two-stage noise aware training using asymmetric deep denoising autoencoder KH Lee, SJ Kang, WH Kang, NS Kim 2016 IEEE International Conference on Acoustics, Speech and Signal …, 2016 | 25 | 2016 |
| Unsupervised representation learning for speaker recognition via contrastive equilibrium learning SH Mun, WH Kang, MH Han, NS Kim arXiv preprint arXiv:2010.11433, 2020 | 23 | 2020 |
| CRIM’s system description for the ASVSpoof2021 challenge WH Kang, J Alam, A Fathan Proc. 2021 Edition of the Automatic Speaker Verification and Spoofing …, 2021 | 22 | 2021 |
| Disentangled speaker and nuisance attribute embedding for robust speaker verification WH Kang, SH Mun, MH Han, NS Kim IEEE Access 8, 141838-141849, 2020 | 21 | 2020 |
| Text-independent speaker verification employing CNN-LSTM-TDNN hybrid networks J Alam, A Fathan, WH Kang Speech and Computer: 23rd International Conference, SPECOM 2021, St …, 2021 | 17 | 2021 |
| Investigation on activation functions for robust end-to-end spoofing attack detection system WH Kang, J Alam, A Fathan Proc. 2021 Edition of the Automatic Speaker Verification and Spoofing …, 2021 | 14 | 2021 |
| WaveNODE: A continuous normalizing flow for speech synthesis H Kim, H Lee, WH Kang, SJ Cheon, BJ Choi, NS Kim arXiv preprint arXiv:2006.04598, 2020 | 13 | 2020 |
| Hybrid network with multi-level global-local statistics pooling for robust text-independent speaker recognition WH Kang, J Alam, A Fathan Proc. of Automatic Speech Recognition and Understanding (ASRU), 2021 | 11 | 2021 |
| Real-time automatic word segmentation for user-generated text WI Cho, SJ Cheon, WH Kang, JW Kim, NS Kim arXiv preprint arXiv:1810.13113, 2018 | 9 | 2018 |
| Mel-spectrogram image-based end-to-end audio deepfake detection under channel-mismatched conditions A Fathan, J Alam, WH Kang 2022 IEEE International Conference on Multimedia and Expo (ICME), 1-6, 2022 | 8 | 2022 |
| Integrated DNN-based model adaptation technique for noise-robust speech recognition KH Lee, WH Kang, TG Kang, NS Kim 2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017 | 8 | 2017 |
| On the impact of the quality of pseudo-labels on the self-supervised speaker verification task A Fathan, J Alam, W Kang NeurIPS ENLSP Workshop, 2022 | 7 | 2022 |
| Gated recurrent context: Softmax-free attention for online encoder-decoder speech recognition H Lee, WH Kang, SJ Cheon, H Kim, NS Kim IEEE/ACM Transactions on Audio, Speech, and Language Processing 29, 710-719, 2021 | 7 | 2021 |
| Hybrid neural network with cross-and self-module attention pooling for text-independent speaker verification J Alam, WH Kang, A Fathan ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023 | 6 | 2023 |
| Deep learning-based end-to-end spoken language identification system for domain-mismatched scenario W Kang, MJ Alam, A Fathan Proceedings of the Thirteenth Language Resources and Evaluation Conference …, 2022 | 6 | 2022 |
| Information Preservation Pooling for Speaker Embedding. MH Han, WH Kang, SH Mun, NS Kim Odyssey, 60-66, 2020 | 6 | 2020 |
| Adversarially learned total variability embedding for speaker recognition with random digit strings WH Kang, NS Kim Sensors 19 (21), 4709, 2019 | 6 | 2019 |
| End-to-End Multi-Channel Speech Enhancement Using Inter-Channel Time-Restricted Attention on Raw Waveform. HS Lee, HY Kim, WH Kang, J Kim, NS Kim Interspeech, 4285-4289, 2019 | 6 | 2019 |
Nam Soo KimSeoul National University, Department of Electrical and Computer EngineeringVerified email at snu.ac.kr
