[논문분석] Diff2Lip: Audio Conditioned Diffusion Models for Lip-Synchronization
Audio Conditioned Diffusion Models - Talking Face generation
최근 포스트
[논문분석] Sound-guided Semantic Video Generation
GAN을 활용한 sound guided video generation, clip의 latent space를 활용
[프로젝트] Korean Audio, Multilingual Hubert translate Training Guideline
기존 Unit based audio Multilingual translate으로 제안된 논문에 Korean을 추가
[프로젝트] Korean Audio, Multilingual Hubert translate Training Challenges
기존 Unit based audio Multilingual translate으로 제안된 논문에 Korean을 추가
[프로젝트] Audio2Video : audio unit based speech video generation with diffusion model - Proposal
Hubert, [Speech audio Unit encoding] conditioning, diffusion video generation