Dongheon Lee

Introduction

Dongheon Lee's Photo

Dongheon Lee

Ph.D. student in Electrical Engineering at Korea Advanced Institute of Science and Technology (KAIST), in Smart Sound Systems under the supervision of Prof. Jung-Woo Choi. My research is focused on deep learning-based single/multi-channel speech enhancement and source separation. My interests also include microphone array signal processing, AR/VR, and automatic speech recognition (ASR).

Contact

Links

Google Scholar LinkedIn CV GitHub

Research Interests

  • Deep learning for speech enhancement and source separation
  • Microphone array signal processing
  • Augmented and virtual reality (AR/VR)
  • Automatic speech recognition (ASR)

Education

  • Ph.D. in Electrical Engineering, KAIST (2020.3 - Present)
  • B.S. in Electrical Engineering, KAIST (2016.03 - 2020.02)
  • Changwon Science Highschool (2014.03 - 2016.02)

Work Experience

  • Research Intern, SK Hynix (2019.06 - 2019.08)

Selected Publications

  • D. Lee, and JW. Choi, "DeFTAN-II: Efficient multichannel speech enhancement with subgroup processing," IEEE/ACM Trans. Audio, Speech, Lang. Process., 2024.
  • D. Lee, and JW. Choi, "DeFTAN-AA: Array geometry agnostic multichannel speech enhancement," in Proc. Interspeech, 2024.
  • D. Lee, D. Choi, and JW. Choi, "Real-time multichannel speech enhancement using Dense Frequency-Time Attentive Network and non-overlapping synthesis window," in Proc. Interspeech, 2023.
  • D. Lee, and JW. Choi, "DeFT-AN: Dense Frequency-Time Attentive Network for multichannel speech enhancement," IEEE Signal Process. Lett., 2023.
  • D. Lee, B. Jo, and JW. Choi, “Direction-of-arrival estimation with blind surface impedance compensation for spherical microphone array,” JASA Express Lett., 2021.