3 papers accepted for APSIPA ASC 2025

References

2025

  1. Drum-to-Vocal Percussion Sound Conversion and Its Evaluation Methodology
    Rinka Nobukawa ,  Makito Kitamura ,  Tomohiko NakamuraShinnosuke Takamichi ,  and  Hiroshi Saruwatari
    In Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) , Oct 2025
  2. Constructing an In-the-Wild Spoken Dialogue Dataset Based on YouTube Dialogue Videos
    Yuki Sato ,  Sanae Yamashita ,  Shinnosuke Takamichi ,  and  Ryuichiro Higashinaka
    In Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) , Oct 2025
  3. Active Learning for Text-to-Speech Synthesis with Informative Sample Collection
    Kentaro Seki ,  Shinnosuke TakamichiTakaaki Saeki ,  and  Hiroshi Saruwatari
    In Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) , Oct 2025