Sunghwan Ahn

According to our database, Sunghwan Ahn authored at least 8 papers between 2021 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

HILCodec: High-Fidelity and Lightweight Neural Audio Codec.

Sunghwan Ahn, Beom Jun Woo, Min Hyun Han, Chanyeong Moon, Nam Soo Kim

IEEE J. Sel. Top. Signal Process., December, 2024

2023

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

Ji Won Yoon, Hyung Yong Kim, Hyeonseung Lee, Sunghwan Ahn, Nam Soo Kim

IEEE ACM Trans. Audio Speech Lang. Process., 2023

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

Ji Won Yoon, Sunghwan Ahn, Hyeonseung Lee, Minchan Kim, Seok Min Kim, Nam Soo Kim

Proceedings of the International Conference on Machine Learning, 2023

Improving Learning Objectives for Speaker Verification from the Perspective of Score Comparison.

Min Hyun Han, Sung Hwan Mun, Minchan Kim, Myeonghun Jeong, Sunghwan Ahn, Nam Soo Kim

Proceedings of the IEEE International Conference on Acoustics, 2023

2022

Inter-KD: Intermediate Knowledge Distillation for CTC-Based Automatic Speech Recognition.

Ji Won Yoon, Beom Jun Woo, Sunghwan Ahn, Hyeonseung Lee, Nam Soo Kim

Proceedings of the IEEE Spoken Language Technology Workshop, 2022

Transfer Learning Framework for Low-Resource Text-to-Speech using a Large-Scale Unlabeled Speech Corpus.

Minchan Kim, Myeonghun Jeong, Byoung Jin Choi, Sunghwan Ahn, Joun Yeop Lee, Nam Soo Kim

Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

VeloxDFS: Streaming Access to Distributed Datasets to Reduce Disk Seeks.

Sunghwan Ahn, Hyeongjun Park, Vicente A. Bolea Sanchez, Deukyeon Hwang, Wonbae Kim, Alan Sussman, Beomseok Nam

Proceedings of the 22nd IEEE International Symposium on Cluster, 2022

2021

Oracle Teacher: Towards Better Knowledge Distillation.

Ji Won Yoon, Hyung Yong Kim, Hyeonseung Lee, Sunghwan Ahn, Nam Soo Kim

CoRR, 2021