Haopeng Geng is currently pursuing a Ph.D. at The University of Tokyo. His research interests lie in solving atypical speech phenomena, such as L2 speech, accented speech, and pathological speech, using deep learning and signal processing methods.

Before joining UTokyo, he worked as an AI software engineer at Laronix, an Australian start-up company that developed the world’s first pneumatic larynx. In this role, he was responsible for evaluating and improving the speech quality of products designed for the voice loss community. He earned his M.S. and B.S. degrees from Nagoya University and Dalian University of Technology (DLUT), respectively.

📝 Publications

Simulating Native Speaker Shadowing for Nonnative Speech Assessment with Latent Speech Representations, Haopeng Geng, Saito Daisuke, Nobuaki Minematsu. Submitting to ICASSP 2025. 🎧Demo
A Pilot Study of Applying Sequence-to-Sequence Voice Conversion to Evaluate the Intelligibility of L2 Speech Using a Native Speaker’s Shadowings, Haopeng Geng, Saito Daisuke, Nobuaki Minematsu. Accepted by APSIPA 2024. 🎧Demo,
Disfluency Removal with Speech Inpainting on Spontaneous Lecture Speech, Haopeng Geng, YASUDA Yusuke, Tomoki Toda. ASJ 2022

📖 Educations

2024.04 - Present,
- Ph.D Candicates. in Engineering, The University of Tokyo, Japan.
- Supervisor: Prof. Nobuaki Minematsu.
2020.04 - 2022.03
- M.S. in Informatics, Nagoya University, Japan.
- Supervisor: Prof. Tomoki Toda.
2014.09 - 2019.06
- B.S. in Computer Science and Technology, Dalian University of Technology,
- B.A. in Japanese, Dalian University of Technology, China.

💬 Work Experiences

2022.03 - 2024.10, AI Software Engineer, Laronix, Australia.

🎖 Honors and Awards

2024.03 SPRING-GX Scholarship, University of Tokyo.
2022.04 Graduate program for real-world data circulation leaders, Nagoya University.
2017.09 Scholarship for outstanding undergraduate students, CSC.

💻 Internships

2021.02, NTT Human Informatics Laboratories, Japan.
2021.08, NTT Human Informatics Laboratories, Japan.