Pil Moo Byun

According to our database, Pil Moo Byun authored at least 6 papers between 2022 and 2025.

Collaborative distances:

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

2025

Temp4Cap: Temporally-aligned Automated Audio Captioning.

Ho-Young Choi, Jae-Heung Cho, Pil Moo Byun, Won-Gook Choi, Joon-Hyuk Chang

Proceedings of the 26th Annual Conference of the International Speech Communication Association, 2025

Optimizing CLAP Reward with LLM Feedback for Semantically Aligned and Diverse Automated Audio Captioning.

Seyun Ahn, Pil Moo Byun, Won-Gook Choi, Joon-Hyuk Chang

Proceedings of the 26th Annual Conference of the International Speech Communication Association, 2025

2024

Generalized Specaugment via Multi-Rectangle Inverse Masking For Acoustic Scene Classification.

Pil Moo Byun, Joon-Hyuk Chang

Proceedings of the IEEE International Conference on Acoustics, 2024

2023

Class Activation Mapping-Driven Data Augmentation: Masking Significant Regions for Enhanced Acoustic Scene Classification.

Pil Moo Byun, Jeong-Hwan Choi, Joon-Hyuk Chang

Proceedings of the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, 2023

Effective Masking Shapes Based Robust Data Augmentation for Acoustic Scene Classification.

Pil Moo Byun, Joon-Hyuk Chang

Proceedings of the 8th IEEE International Conference on Network Intelligence and Digital Content, 2023

2022

Multi-Scale Architecture and Device-Aware Data-Random-Drop Based Fine-Tuning Method for Acoustic Scene Classification.

Joo-Hyun Lee, Jeong-Hwan Choi, Pil Moo Byun, Joon-Hyuk Chang

Proceedings of the 7th Workshop on Detection and Classification of Acoustic Scenes and Events 2022, 2022