Jongha Kim

AI Researcher @ Sogang University
Audio-Language Intelligence
LALMs & Robust ASR

I am an M.S. student in Artificial Intelligence at Sogang University, advised by Prof. Hyung-Min Park at the Intelligent Information Processing Lab (IIP). I study robust automatic speech recognition and its integration with language models, with applications to the medical domain.

My interest is in multimodal generation — models that understand and generate across speech, vision, and language rather than a single modality. Recently I have focused on robust ASR and its integration with language models, following earlier work on diffusion-based video generation (scene-graph conditioning, talking-face synthesis) and speech-unit translation.

I received my B.S. in Electronic Engineering from Inha University in August 2025, and joined the IIP Lab as a research intern before starting the M.S. program in March 2026.

Research Interests

  • Speech & Language — robust ASR, language model integration, speech enhancement
  • Multimodal Generation — audio–visual–text representation, speech-to-speech translation
  • Generative Models — diffusion models, transformer architectures, video synthesis

Experience

Graduate Researcher · Mar. 2026 – Present Intelligent Information Processing Lab (IIP), Sogang University

  • Robust automatic speech recognition for the medical domain (SCH).
  • Integration of robust ASR with language models.

Research Intern · Jul. 2025 – Feb. 2026 Intelligent Information Processing Lab (IIP), Sogang University

Joined the lab before the M.S. program.

ML Scientist / Embedded Engineer · Mar. 2025 – Jun. 2025 R&D Department, STS Engineering

  • Soft-sensor prediction of water quality indicators from IoT sensor time series.
  • MCU firmware on FreeRTOS for continuous unattended operation.

Research Intern · Jan. 2024 – Dec. 2024 Machine Intelligence Lab, Inha University

  • Video synthesis with diffusion models; scene-graph-conditioned video generation.
  • Long video generation.

Research Intern · Jul. 2022 – Dec. 2022 Intelligence Embedding System Lab (IESL), Inha University

  • Computer vision for robotics and autonomous driving.

Education

Sogang University, Seoul, Korea · Mar. 2026 – Present M.S. Student, Department of Artificial Intelligence

Intelligent Information Processing Lab (IIP) · Advisor: Prof. Hyung-Min Park

Inha University, Incheon, Korea · Feb. 2019 – Aug. 2025 B.S. in Electronic Engineering

GPA 3.98 / 4.5

Publications

  1. “TASK-LEAF ROUTED MIMO-AUDIO FOR DCASE 2026 TASK 5.” Detection and Classification of Acoustic Scenes and Events (DCASE) 2026 Challenge, Jul. 1, 2026. Ranked 6th out of 11 lightweight systems.
  2. Jang Ji-hye, Lee Young-jun, Heo Ji-won, Kim Jong-ha. “Development of an ROS-based Environmental Perception and Decision-making System for Indoor Autonomous Mobile Robots.” Korean Society of Automotive Engineers (KSAE), Jeju, Korea, Oct. 2022. (Poster)

Awards

  • Academic Excellence Scholarship, Inha University — Mar. 2024
  • Encouragement Prize, Convergence Project 2022-2, Inha University — Dec. 2022
  • Encouragement Award, Winter Break Job Analysis Online Competition, Inha University — Jan. 2023

Skills

  • Programming — Python, C, C++, Linux
  • Frameworks — PyTorch (Lightning), TensorFlow, Fairseq
  • Certifications — SQLD (SQL Developer), ADSP (Advanced Data Analytics Semi-Professional)

See Projects for research and engineering work, or CV for the full record. Earlier paper-review notes are kept at moos-tudy.tistory.com.