关äŗŽ

AI Researcher & Speech Processing

Ph.D. Student, Toda Lab., Nagoya University

Ph.D. in Speech Processing, Speech Generation. I am interested in a research or industry role involving the Generation Model, LLM, Robust Generation, and AI in Health.

Besides research, I enjoy hiking, scuba diving, and other outdoor activities.

šŸŽ“ Education

DegreeFieldUniversity
Ph.D.InformaticsNagoya University
M.Sc.EngineeringNagoya University
B.Sc.Software EngineeringShandong University

šŸ”¬ Research Experience

šŸŽ“ Ph.D. @Nagoya Univ. (2022.4 -)

  • My Ph.D. work focused on training robust speech generation models on low-quality data.

šŸ§‘šŸ»ā€šŸ’» Research Internship @Sony R&D (2024.2 - 2024.3)

  • Multilingual speech synthesis

šŸŽ“ M.Sc. @Nagoya Univ. (2020.4 - 2022.3)

  • Interaction of empathy educational robots by synthesized speech

šŸ“œ Publications

  1. J. Feng, Y. Yasuda, T. Toda, Exploring the robustness of text-to-speech synthesis based on diffusion probabilistic models to heavily noisy transcriptions, Proc. INTERSPEECH, pp. 4408-4412, Kos Island, Greece, Sep. 2024.
  2. J. Feng, T. Yoshikawa, T. Toda, Interpretable control for emotional text-to-speech system toward development of sympathetic educational-support robots, Proc. APSIPA ASC, pp. 342-346, Chiang Mai, Thailand, Nov. 2022.
  3. J. Feng, T. Yoshikawa, T. Toda, Interpretable emotional control for text-to-speech system toward development of sympathetic educational-support robots, éŸ³č¬›č«–, 3-8-3, pp. 1189-1190, Sep. 2022.

šŸ“Œ Honors and Activity

© 2024 - 2026 J. Feng
ä½æē”Ø Hugo Ꞅå»ŗ
äø»é¢˜ Stack ē”± Jimmy č®¾č®”