Jeongsoo Choi
11 papers · 2022–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
π Conference Polyglot (6) π Cross-Pollinator (4) π§ Keyword Pioneer π Interdisciplinary Bridge π Renaissance Researcher (7)
πΊοΈ
Taxonomy Completionist
(25)
π§
Keyword Pioneer
π
Trend Setter
β‘
Prolific Year
(5)
π
Century Club
(11)
ποΈ
Keyword Collector
(57)
Conferences
ICCV (4)
CVPR (3)
AAAI (1)
EMNLP (1)
ICLR (1)
INTERSPEECH (1)
Top co-authors
Keywords
multimodal learning
(4)
flow matching
(3)
speech synthesis
(2)
facial animation
(2)
video-to-speech synthesis
(2)
diffusion model
(2)
lip synchronization
(2)
lip-sync
(1)
talking face generation
(1)
transfer learning
(1)
speech recognition
(1)
low-resource language
(1)
cross-modal learning
(1)
self-supervised learning
(1)
hierarchical representation
(1)
face animation
(1)
speaker verification
(1)
audio-visual fusion
(1)
speaker embedding
(1)
audio-visual synthesis
(1)
Papers
From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech
CVPR 2025
MAVFlow: Preserving Paralinguistic Elements with Conditional Flow Matching for Zero-Shot AV2AV Multilingual Translation
ICCV 2025
VoiceCraft-Dub: Automated Video Dubbing with Neural Codec Language Models
ICCV 2025
ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video Generation
ICLR 2025
Dub-S2ST: Textless Speech-to-Speech Translation for Seamless Dubbing
EMNLP 2025
AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation
CVPR 2024
Intelligible Lip-to-Speech Synthesis with Speech Units
INTERSPEECH 2023
Watch or Listen: Robust Audio-Visual Speech Recognition With Visual Corruption Modeling and Reliability Scoring
CVPR 2023
DiffV2S: Diffusion-Based Video-to-Speech Synthesis with Vision-Guided Speaker Embedding
ICCV 2023
Lip Reading for Low-resource Languages by Learning and Combining General Speech Knowledge and Language-specific Knowledge
ICCV 2023
SyncTalkFace: Talking Face Generation with Precise Lip-Syncing via Audio-Lip Memory
AAAI 2022