Hien Ohnaka

icon.jpg

I’m a master student of Nara Institute of Science and Technology (NAIST), Japan. My professor is Koichiro Yoshino. Also, I’m a part-time job engineer/researcher at LY corp.

My reseach interests are spoken language processing and audio signal processing.

selected publications

  1. Speech synthesis
    Peer-reviewed
    First
    Wave-Trainer-Fit: Neural Vocoder with Trainable Prior and Fixed-Point Iteration towards High-Quality Speech Generation from SSL features
    Hien Ohnaka, Yuma Shirahata, and Masaya Kawamura
    In Accepted to IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2026
  2. Sound synthesis
    Peer-reviewed
    First
    Visual Onoma-to-Wave: Environmental Sound Synthesis from Visual Onomatopoeias and Sound-Source Images
    Hien Ohnaka, Shinnosuke Takamichi, Keisuke Imoto, and 3 more authors
    In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Jun 2023
    DOI arXiv Code Website
  3. Speech enhancement
    Peer-reviewed
    First
    Unsupervised speech enhancement with spectral kurtosis and double deep priors
    Hien Ohnaka and Ryoichi Miyazaki
    Acoustical Science and Technology, Feb 2025
    DOI arXiv Code
  4. Speech synthesis
    Peer-reviewed
    First
    Grapheme-Coherent Phonemic and Prosodic Annotation of Speech by Implicit and Explicit Grapheme Conditioning
    Hien Ohnaka, Yuma Shirahata, Byeongseon Park, and 1 more author
    In Proceedings of Interspeech, Aug 2025
    DOI arXiv