CCQA: Generating Question from Solution Can Improve Inference-Time Reasoning in SLMs

J. Kim and J. W. Yoon

Proc. EMNLP (main), 2025.

Heuristic-free Knowledge Distillation for Streaming ASR via Multi-modal Training

J. W. Yoon

Proc. AAAI, 2025.

HuBERT-EE: Early Exiting HuBERT for Efficient Speech Recognition

J. W. Yoon, B. J. Woo, and N. S. Kim

Proc. Interspeech, 2024.

* Oral presentation

EM-Network: Oracle Guided Self-distillation for Sequence Learning

J. W. Yoon, S. Ahn, H. Lee, M. Kim, S. M. Kim, and N. S. Kim

Proc. ICML, 2023. 

Oracle Teacher: Leveraging Target Information for Better Knowledge Distillation of CTC Models

J. W. Yoon, H. Y. Kim, H. Lee, S. Ahn, and N. S. Kim

IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 31, pp. 2974-2987, 2023. 

MCR-Data2vec 2.0: Improving Self-supervised Speech Pre-training via Model-level Consistency Regularization

J. W. Yoon, S. M. Kim, and N. S. Kim

Proc. Interspeech, 2023.

TutorNet: Towards Flexible Knowledge Distillation for End-to-End Speech Recognition

J. W. Yoon, H. Lee, H. Y. Kim, W. I. Cho, and N. S. Kim

IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 29, pp. 1626-1638, 2021.