Multimodal AI Lab

Recruiting grad students

KAIST · Graduate School of Metaverse

Information sourcenot verified yet

This lab is recruiting graduate students

머신러닝, 음성 처리, 컴퓨터 비전에 관심 있는 학생을 모집한다고 홈페이지에 명시.

Check the professor and homepage links below for how to reach out.

Ask current students about this lab

Post your question to the Career board — students who have verified their school can answer under blind identities.

Professor

Prof. 정준선

Professor's page · publications

About

KAIST 전기및전자공학부 소속 정준선(Joon Son Chung) 교수의 멀티모달 AI 연구실(Multimodal AI Lab)로, 메타버스대학원 참여 연구실이다. 음성 처리와 컴퓨터 비전을 결합한 멀티모달 AI를 연구하며, 오디오-비주얼 음성 분석, 토킹 페이스 생성, 음원 위치 추정, 음성 생성 등을 다룬다.

Research keywords

AI & Machine LearningMultimedia Signal ProcessingHuman Computer Interaction

Selected publications

Let There Be Sound: Reconstructing High Quality Speech from Silent VideosAAAI · 2024
VoiceLDM: Text-to-Speech with Environmental ContextICASSP · 2024
Seeing Through the Conversation: Audio-Visual Speech Separation based on Diffusion ModelICASSP · 2024
Can CLIP Help Sound Source Localization?WACV · 2024
That's What I Said: Fully-Controllable Talking Face GenerationACM MM · 2023
Sound Source Localization is All about Cross-Modal AlignmentICCV · 2023

Other labs in this department

See all labs in this department