june-oh (RiceBerry) · GitHub
Skip to content
View june-oh's full-sized avatar
🎯
Focusing
🎯
Focusing
6 followers · 3 following

Highlights

  • Pro

Block or report june-oh

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
june-oh/README.md

👋 Hi there! I'm Junseok Oh (오준석) aka june-oh or RiceBerry

🎓 Ph.D. in Computer Science and Engineering (Aug 2026) @ Sogang University, Auditory Intelligence Lab
🔬 Advised by Prof. Ji-Hwan Kim

Portfolio Google Scholar LinkedIn Email

🔬 Research Focus

Speech Recognition × Large Language Models

  • 🎙️ ASR: Streaming, Context-biasing, Domain Adaptation
  • 🤖 Speech-LLM: Adapter-based Integration, Multimodal AI
  • 📊 Speech Analytics: Speaking Assessment, Dysarthria Analysis

📝 Recent Publications

Year Paper Venue
2026 Retention-Preserving Gradient Projection for Rehearsal-Free Continual ASR Interspeech 2026 (Accepted)
2026 Adapter-Only Bridging of Frozen Speech Encoder & LLM PAKDD 2026, LNCS vol. 16600 (Oral)
2026 SEAM: Bridging Temporal-Semantic Gap for Speech-LLM EACL Findings
2025 HiTCA: Hierarchical Text & Contextual Audio for VCR EURASIP JASM (Under Review)

💻 Tech Stack

NeMo Whisper Transformers Kaldi

Pinned Loading

  1. watch-party-overlay-timer watch-party-overlay-timer Public

    브라우저 확장 프로그램으로, 비디오 위에 시간, 화수 등의 정보를 오버레이하여 OBS와 같은 소프트웨어로 스트리밍 또는 녹화 시 쉽게 캡처할 수 있도록 도와줍니다.

    JavaScript

  2. 2023_AI_Academy_ASR 2023_AI_Academy_ASR Public

    🎙️ Deep Learning ASR Tutorial - Audio handling, MLP, CTC, Whisper, NeMo finetuning, WFST with PyTorch & Colab notebooks

    Jupyter Notebook 3 4

  3. 2024_cseg109 2024_cseg109 Public

    📚 Sogang Univ. CSEG109/AIEG109 Lab - Audio processing, Language Models, FastSpeech2 TTS with PyTorch & Colab

    Jupyter Notebook 1 1

  4. june-oh june-oh Public

    profile

    Astro