CV

[Download Full CV (PDF)]

Education

• Ph.D. Student, The University of Tokyo, Apr. 2025 ~ Present
  • Department of Information Physics & Computing, Graduate School of Information Science and Technology
  • Research Theme: Towards integrated audio generation model based on linguistic analysis of speech token and automatic evaluation of acoustic signals
  • Advisor: Yuki Saito
• Master’s Degree, The University of Tokyo, Apr. 2023 ~ Mar. 2025
  • Department of Electrical Engineering & Information Systems, Graduate School of Engineering
  • Thesis: A Study on Analysis of Discrete Speech Representation Using Self-Supervised Learning Model and its Application to Speech Synthesis
  • Advisor: Daisuke Saito / GPA: 3.0 / 3.0
• Bachelor’s Degree, Sogang University, Mar. 2016 ~ Feb. 2022
  • Major in Artificial Intelligence, Department of Electronic Engineering, School of Engineering
  • Thesis: Development of an Interactive Voice User Interface in Kiosk System Using Deep Learning
  • Advisor: Hyung-Min Park / GPA: 3.54 / 4.3

Work Experiences

• Spellbrush — Researcher (Part-time), Oct. 2025 ~ Present
  • Research on speech generation in multimodal dialogue models and video generation models
• CoeFont Co., Ltd. — Researcher (Part-time), Apr. 2023 ~ Mar. 2026
  • Improvement and acceleration of the self-supervised learning framework for real-time speech synthesis and voice conversion
• Cygames Inc. — Researcher (Part-time), Oct. 2024 ~ Jun. 2025
  • Research on real-time foley sound synthesis in the virtual environment
• Preferred Networks Inc. — Researcher (Internship), Aug. 2024 ~ Oct. 2024
  • Research on multilingual emotional speech synthesis with spherical vectors and discrete speech tokens
• NTT R&D — Researcher (Internship), Jan. 2024 ~ Feb. 2024
  • Analysis towards g2p-free speech synthesis using Text-Speech token encoder through Hidden-Unit T5
• DeNA Co., Ltd. — AI Specialist (Internship), Aug. 2023 ~ Oct. 2023
  • Improvement and implementation of cross-lingual voice conversion for products
• Samsung Medical Center — Research Assistant (Part-time), Sep. 2020 ~ Jun. 2021
  • Optimization of classification model and distillation of datasets for detecting diseases from cardiac MRI

Research Experiences

• LY Corporation — Industry-Academic Collaborative Research, Apr. 2025 ~ Present
  • Research on generating speech-to-face expression generation for virtual avatar
• Darrell Group, University of California, Berkeley — Visiting Scholar, Jun. 2024 ~ Jul. 2024
  • Research on analyzing the language of text-derived tokens from various modalities
• Saruwatari & Koyama Lab, The University of Tokyo — Research Student, Apr. 2022 ~ Mar. 2023
  • Research on self-supervised learning and generative model on speech synthesis for speech enhancement
• Intelligent Information Processing Lab, Sogang University — Internship, Oct. 2021 ~ Mar. 2022
  • Development of dialogue system and speech synthesis in IIPERIA
• Auditory Intelligent Lab, Sogang University — Internship, Jan. 2021 ~ Jun. 2021
  • Development of SGRecognizer Demo: Korean unlimited vocabulary speech recognition system using Kaldi

Honors and Scholarships

• JSPS DC2 Research Fellowship (Accepted), Apr. 2026 ~ Mar. 2028
  • Japan Society for the Promotion of Science, 200,000 JPY/month + Research Funds
• Best Paper Award, Sound Symposiums 2025, Jun. 2025
• Best Student Paper Award (LY Corporation Award), 154th Conference on Spoken Language Processing (SLP), Dec. 2024
• Honorable Mention Award, ETRI OpenAPI Competition, Nov. 2022
• Japanese Government (MEXT) Scholarship, Apr. 2022 ~ Mar. 2026
  • 147,000 JPY/month
• Best Undergraduate Paper Award, Korean Information Science Society, May 2021

Skills

• Technologies
  • Libraries: NumPy, pandas, PyTorch, Kaldi etc.
  • Programming Languages: Python, C, MATLAB, shell, HTML/CSS
  • Software Development Tools: Git, Docker, Jupyter, VS Code etc.
• Spoken Languages
  • Korean (Native), English, Japanese (Near Native), Chinese (Fully Professional)

Publications

MixedG2P-T5: G2P-free Speech Synthesis for Mixed-script Texts using Speech Self-Supervised Learning and Language Model

Joonyong Park, Daisuke Saito, Nobuaki Minematsu. (2025). "MixedG2P-T5: G2P-free Speech Synthesis for Mixed-script Texts using Speech Self-Supervised Learning and Language Model." APSIPA 2025.

Analysing the Language of Neural Audio Codecs

Joonyong Park, Shinnosuke Takamichi, David M. Chan, Shunsuke Kando, Yuki Saito, Hiroshi Saruwatari. (2025). "Analysing the Language of Neural Audio Codecs." Proc. IEEE ASRU, 2025.

EmoSSLSphere: Multilingual Emotional Speech Synthesis with Spherical Vectors and Discrete Speech Tokens

Joonyong Park, Kenichi Nakamura. (2025). "EmoSSLSphere: Multilingual Emotional Speech Synthesis with Spherical Vectors and Discrete Speech Tokens." Proc. ICSA SSW, 2025.

Analyzing the Language of Visual Tokens

David M. Chan, Rodolfo Corona, Joonyong Park, Cheol Jun Cho, Yutong Bai, Trevor Darrell. (2025). "Analyzing the Language of Visual Tokens." Submitted to ACL ARR, 2025.

Analytic Study of Text-Free Speech Synthesis for Raw Audio using a Self-Supervised Learning Model

Joonyong Park, Daisuke Saito, Nobuaki Minematsu. (2024). "Analytic Study of Text-Free Speech Synthesis for Raw Audio using a Self-Supervised Learning Model." APSIPA ASC 2024.

A Pilot Study of GSLM-based Simulation of Foreign Accentuation Only Using Native Speech Corpora

Kentaro Onda, Joonyong Park, Nobuaki Minematsu, Daisuke Saito. (2024). "A Pilot Study of GSLM-based Simulation of Foreign Accentuation Only Using Native Speech Corpora." Proc. ISCA INTERSPEECH, 2024.

Do Learned Speech Symbols Follow Zipf’s Law?

Shinnosuke Takamichi, Hiroki Maeda, Joonyong Park, Daisuke Saito, Hiroshi Saruwatari. (2024). "Do Learned Speech Symbols Follow Zipf's Law?" ICASSP 2024, pp. 12526-12530.

How Generative Spoken Language Modeling Encodes Noisy Speech: Investigation from Phonetics to Syntactics

Joonyong Park, Shinnosuke Takamichi, Tomohiko Nakamura, Kentaro Seki, Detai Xin, Hiroshi Saruwatari. (2023). "How Generative Spoken Language Modeling Encodes Noisy Speech: Investigation from Phonetics to Syntactics." Interspeech 2023, pp. 1085-1089.