publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2025

  1. ICASSP
    fig_vrvq.png
    Variable Bitrate Residual Vector Quantization for Audio Coding
    Yunkee Chae, Woosung Choi, Yuhta Takida, and 8 more authors
    In ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    Work done during internship at Sony AI , 2025
    DOI arXiv Code Website
  2. Preprint
    fig_mge.png
    MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extraction
    Yunkee Chae and Kyogu Lee
    arXiv preprint arXiv:2505.23305, 2025
    arXiv Code Website
  3. Interspeech
    fig_nvrvq.png
    Towards Bitrate-Efficient and Noise-Robust Speech Coding with Variable Bitrate RVQ
    Yunkee Chae and Kyogu Lee
    In Interspeech 2025, 2025
    arXiv Code Website

2024

  1. Interspeech
    fig_lyrics.png
    Song Form-aware Full-Song Text-to-Lyrics Generation with Multi-Level Granularity Syllable Count Control
    Yunkee Chae, Eunsik Shin, Hwang Suntae, and 2 more authors
    In Interspeech 2025, 2024
    arXiv Code Website

2023

  1. ACM MM
    fig_music_enhancement.png
    Exploiting Time-Frequency Conformers for Music Audio Enhancement
    Yunkee Chae, Junghyun Koo, Sungho Lee, and 1 more author
    In Proceedings of the 31st ACM International Conference on Multimedia, Ottawa ON, Canada, 2023
    DOI arXiv Code Website
  2. ISMIR
    fig_pseudo_mss.png
    Self-Refining of Pseudo Labels for Music Source Separation With Noisy Labeled Data
    Junghyun Koo*, Yunkee Chae*, Chang-Bin Jeon, and 1 more author
    In Proceedings of the 24th International Society for Music Information Retrieval Conference , Nov 2023
    DOI arXiv
  3. Interspeech
    fig_dsr.png
    Debiased automatic speech recognition for dysarthric speech via sample reweighting with sample affinity test
    Eungbeom Kim*, Yunkee Chae*, Jaeheon Sim, and 1 more author
    In Interspeech 2023, Nov 2023
    arXiv
  4. ICASSP
    fig_showme.png
    Show Me the Instruments: Musical Instrument Retrieval From Mixture Audio
    Kyungsu Kim*, Minju Park*, Haesun Joung*, and 4 more authors
    In ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Nov 2023
    DOI arXiv Code Website