Ji Sub Um

According to our database, Ji Sub Um authored at least 4 papers between 2022 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2025

How Far Do SSL Speech Models Listen for Tone? Temporal Focus of Tone Representation under Low-resource Transfer.

Minu Kim, Ji Sub Um, Hoirin Kim

CoRR, November, 2025

2024

Utilizing Adaptive Global Response Normalization and Cluster-Based Pseudo Labels for Zero-Shot Voice Conversion.

Ji Sub Um, Hoirin Kim

Proceedings of the 25th Annual Conference of the International Speech Communication Association, 2024

2022

ACNN-VC: Utilizing Adaptive Convolution Neural Network for One-Shot Voice Conversion.

Ji Sub Um, Yeunju Choi, Hoi Rin Kim

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

Anti-Spoofing Using Transfer Learning with Variational Information Bottleneck.

Youngsik Eom, Yeonghyeon Lee, Ji Sub Um, Hoi Rin Kim

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