J-GLOBAL ID:201801003254494892   Update date: Jun. 18, 2024


ヤスダ ユウスケ | YASUDA Yusuke
Affiliation and department:
Job title: Project Lecturer
Research field  (1): Perceptual information processing
Research theme for competitive and other funds  (2):
  • 2024 - 2029 合成メディアの大規模比較評価の最適化と主観比較評価コーパスの構築
  • 2024 - 2025 大規模主観比較評価コーパス構築のための比較評価の動的最適化
Papers (25):
  • Yusuke Yasuda, Tomoki Toda. Automatic design optimization of preference-based subjective evaluation with online learning in crowdsourcing environment. ArXiv. 2024
  • 安田裕介, 戸田智基. クラウドソーシングを用いた大規模 比較評価のための評価ペアの組み合わせと評価数のオンライン最適化. 音講論. 2024. 春. 2-P-39. 1057-1060
  • Statistical analysis of listening test of synthetic speech. 2023. 1-3Q-11. 841-844
  • Cheng-Hung Hu, Yusuke Yasuda, Tomoki Toda. Preference-based training framework for automatic speech quality assessment using deep neural network. Interspeech. 2023
  • Yusuke Yasuda, Tomoki Toda. Analysis of mean opinion scores in subjective evaluation of synthetic speech based on tail probabilities. Interspeech. 2023
MISC (1):
  • Xin Wang, Yusuke Yasuda, Shinji Takaki, Junichi Yamagishi. Overview of NII open-source DNN speech synthesis toolkits: towards reproducible speech synthesis research environments. IEEE SLT worksop
Patents (2):
  • 音声合成装置
  • 情報処理装置、情報処理システム、プログラムおよび情報処理方法
Lectures and oral presentations  (1):
  • Tutorial on end-to-end text-to-speech synthesis Part 2 - Tactron and related end-to-end systems
    (January meetup, SP 2019)
Awards (2):
  • 2023/09 - 日本音響学会 第2回 音声合成研究奨励賞吉田賞
  • 2019/12 - Acoustical Society of Japan Student best paper award Toward end-to-end text-to-speech synthesis without soft attention.
※ Researcher’s information displayed in J-GLOBAL is based on the information registered in researchmap. For details, see here.

Return to Previous Page