Jeongsoo Choi
Scholar

Jeongsoo Choi

Google Scholar ID: WPcjsEkAAAAJ
KAIST
Computer VisionSpeech ProcessingMachine Learning
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
398
 
H-index
9
 
i10-index
9
 
Publications
20
 
Co-authors
12
list available
Contact
CVOpen ↗GitHubOpen ↗LinkedInOpen ↗
Publications
10 items
DiFlowDubber: Discrete Flow Matching for Automated Video Dubbing via Cross-Modal Alignment and Synchronization
2026
Cited
0
Dub-S2ST: Textless Speech-to-Speech Translation for Seamless Dubbing
2025
Cited
0
Accelerating Diffusion-based Text-to-Speech Model Training with Dual Modality Alignment
2025
Cited
0
AlignDiT: Multimodal Aligned Diffusion Transformer for Synchronized Speech Generation
2025
Cited
0
VoiceCraft-Dub: Automated Video Dubbing with Neural Codec Language Models
2025
Cited
0
From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech
2025
Cited
0
MAVFlow: Preserving Paralinguistic Elements with Conditional Flow Matching for Zero-Shot AV2AV Multilingual Translation
2025
Cited
0
Deep Understanding of Sign Language for Sign to Subtitle Alignment
2025
Cited
0
Resume (English only)
Background
  • Research interest includes 1) Multilingual and Multimodal Machine Translation and 2) Audio-Visual Speech Recognition and Generation.
Co-authors
12 total
Yong Man Ro
Yong Man Ro
Professor of Electrical Engineering, KAIST, ICT Endowed Chair Professor
Minsu Kim
Minsu Kim
Google DeepMind
Se Jin Park
Se Jin Park
Korea Advanced Institute of Science and Technology (KAIST)
Joanna Hong
Joanna Hong
Google DeepMind
Joon Son Chung
Joon Son Chung
KAIST
Jeong Hun Yeo
Jeong Hun Yeo
Korea Advanced Institute of Science and Technology
Ji-Hoon Kim
Ji-Hoon Kim
KAIST
Shujie Liu (刘树杰）
Shujie Liu (刘树杰）
Microsoft Research Asia