Eunseop Yoon
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper proposes Visual Gradient Steering (VGS), a method that decomposes the distillation loss into language and visual components and steers the optimization to prioritize visual grounding, significantly improving vision-language reasoning.
The paper proposes RTFree-F5, a method to make flow-matching TTS models like F5-TTS independent of reference transcripts, improving performance and naturalness for dysarthric speakers.
Papers
Transcript-Free Flow-Matching Text-to-Speech via Speech Feature Conditioning
SooHwan Eom, Hee Suk Yoon, Eunseop Yoon, Mark Hasegawa-Johnson +1 more
The paper proposes RTFree-F5, a method to make flow-matching TTS models like F5-TTS independent of reference transcripts, improving performance and naturalness for dysarthric speakers.