Education
Sep. 2015 - Feb. 2020
M.S. and Ph.D. in Electrical and Electronics, Yonsei University, Seoul, Korea
• Department of Electrical and Electronics
• Thesis : “LP-WaveNet: Linear Prediction-based WaveNet Speech Synthesis”
• Supervisor : Prof. Hong-Goo Kang
Mar. 2011 - Aug. 2015
B.S. in Electrical and Electronics, Yonsei University, Souel, Korea
• Department of Electrical and Electronics
Work Experience
May. 2024 - Present
Research Scientist, Meta AI, Seattle, Washington, USA
• Presently researching expressive conversational AI voice agent.
• Presently researching expressive speech-to-speech translation system.
Oct. 2022 - May. 2024
Postdoctoral Researcher, Meta AI, Seattle, Washington, USA
• Researched expressive speech-to-speech translation system.
• Developed PRETSSEL, which is core module of Meta’s expressivity-preserving S2ST system.
May. 2019 - Sep. 2022
Research Scientist, Naver Clova, Seongnam, Korea
• Primarily researched the high-quality and fast neural vocoding system.
• Developed and adopted various neural vocoders for various TTS services at Naver.
• Developed PyTorch-based TTS toolkit to build high-quality, fast, and controllable GPU TTS system.
Jan. 2018 - Nov. 2018
Research Intern, Microsoft Research Asia, Beijing, China
• Researched the topic of WaveNet vocoders for high-quality TTS system.
• Investigated the methodologies to adopt the traditional speech processing approach to the neural vocoding systems.
• Mentor: Frank K. Soong
Dec. 2017 - Dec. 2017
Research Intern, Naver Clova, Seongnam, Korea
• Researched the topic of glottal vocoder-based parametric TTS system.
Academic Activites
Reviewer
• 2022 Interspeech, 2022
• EURASIP Journal on Audio, Speech, and Music Processing, 2018
Academic Services
• Session chair, 2021 Interspeech, Session <Thu-M-V-3 source separation>, Sep. 2021
Talks
• “Expressive Speech-to-Speech Translation”, BISH Bash, Feb. 2024 [slide]
• “Voice Synthesis and Application”, KAIST and SNU, Apr. - May. 2022 [slide]
• “High-fidelity Parallel WaveGAN with Harmonic-plus-Noise Model”, Naver Clova, Jul. 2021 [slide]
• “Low-cost and High-quality TTS based on TTS-driven Data Augmentation”, Naver Clova, Jan. 2021
• “TTS-driven Data Augmentation for Fast and High-quality Speech Synthesis”, Naver Clova, Oct. 2020 [slide]
• “High-quality DNN-TTS”, Naver Clova, Oct. 2019
• “Toward WaveNet Speech Synthesis”, Naver Clova, Dec. 2018 [slide]
Teaching
• Signal and Systems (EEE2060.05-00), 2016
• Electrical and Electronic Engineering Experiments: Fundamental (EEE211.01-00), 2015
Honors and Awards
• 2nd place, N Innovation Award 2020, Naver Corp., Dec. 2020
• Best paper award, APSIPA ASC 2020, Dec. 2020
• 1st place, N Innovation Award 2019, Naver Corp., Dec. 2019
• Award of Excellence, Microsoft Research Asia, Nov. 2018
• National Science & Technology Scholarship, Sep. 2013 - Feb. 2015 (about $7,000 per year)
Patent Applications
• KR 10-2022-0047188, “Method and System for Synthesizing Emotional Speech based on Emotion Prediction”, Apr. 2022
• KR 10-2022-0012736, “Neural Network for Speech Synthesis Based on Selective Self-augmentation Algorithm”, Jan. 2022
• KR 10-2022-0012736, “Method and System for Non-autoregressive Speech Synthesis”, Aug. 2021