TutorNet: Towards flexible knowledge distillation for end-to-end speech recognition JW Yoon, H Lee, HY Kim, WI Cho, NS Kim IEEE/ACM Transactions on Audio, Speech, and Language Processing 29, 1626-1638, 2021 | 29 | 2021 |
Speech to text adaptation: Towards an efficient cross-modal distillation WI Cho, D Kwak, JW Yoon, NS Kim arXiv preprint arXiv:2005.08213, 2020 | 27 | 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 |
Speech intention understanding in a head-final language: A disambiguation utilizing intonation-dependency WI Cho, HS Lee, JW Yoon, SM Kim, NS Kim arXiv preprint arXiv:1811.04231, 2018 | 15 | 2018 |
Inter-KD: Intermediate Knowledge Distillation for CTC-Based Automatic Speech Recognition JW Yoon, BJ Woo, S Ahn, H Lee, NS Kim 2022 IEEE Spoken Language Technology Workshop (SLT), 280-286, 2023 | 8 | 2023 |
Hubert-ee: Early exiting hubert for efficient speech recognition JW Yoon, BJ Woo, NS Kim arXiv preprint arXiv:2204.06328, 2022 | 8 | 2022 |
Neurally Optimized Decoder for Low Bitrate Speech Codec HY Kim, JW Yoon, WI Cho, NS Kim IEEE Signal Processing Letters, 2021 | 5 | 2021 |
Oracle Teacher: Towards Better Knowledge Distillation JW Yoon, HY Kim, H Lee, S Ahn, NS Kim arXiv preprint arXiv:2111.03664, 2021 | 1 | 2021 |
Oracle Teacher: Leveraging Target Information for Better Knowledge Distillation of CTC Models JW Yoon, HY Kim, H Lee, S Ahn, NS Kim IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2023 | | 2023 |
EM-Network: Oracle Guided Self-distillation for Sequence Learning JW Yoon, S Ahn, H Lee, M Kim, SM Kim, NS Kim arXiv preprint arXiv:2306.10058, 2023 | | 2023 |
MCR-Data2vec 2.0: Improving Self-supervised Speech Pre-training via Model-level Consistency Regularization JW Yoon, SM Kim, NS Kim arXiv preprint arXiv:2306.08463, 2023 | | 2023 |
Method and apparatus with abnormal channel of microphone array detection and compensation signal generation NS Kim, JW Yoon US Patent App. 17/689,299, 2023 | | 2023 |
EM-Network: Learning Better Latent Variable for Sequence-to-Sequence Models JW Yoon, SH Ahn, H Lee, M Kim, SM Kim, NS Kim | | 2022 |