5 papers
Hear What Matters! Text-conditioned Selective Video-to-Audio Generation
Junwon Lee, Juhan Nam, Jiyoung Lee
This work introduces a new task, text-conditioned selective video-to-audio (V2A) generation, which produces only the user-intended sound from a multi-object video. This capability…
Referee: Reference-aware Audiovisual Deepfake Detection
Hyemin Boo, Eunsang Lee, Jiyoung Lee
Deepfakes generated by advanced generative models have rapidly posed serious threats, yet existing audiovisual deepfake detection approaches struggle to generalize to unseen manipu…
Erasing Your Voice Before It's Heard: Training-free Speaker Unlearning for Zero-shot Text-to-Speech
Myungjin Lee, Eunji Shin, Jiyoung Lee
Modern zero-shot text-to-speech (TTS) models offer unprecedented expressivity but also pose serious crime risks, as they can synthesize voices of individuals who never consented. I…
CountSteer: Steering Attention for Object Counting in Diffusion Models
Hyemin Boo, Hyoryung Kim, Myungjin Lee +4
Text-to-image diffusion models generate realistic and coherent images but often fail to follow numerical instructions in text, revealing a gap between language and visual represent…
TwinShift: Benchmarking Audio Deepfake Detection across Synthesizer and Speaker Shifts
Jiyoung Hong, Yoonseo Chung, Seungyeon Oh +4
Audio deepfakes pose a growing threat, already exploited in fraud and misinformation. A key challenge is ensuring detectors remain robust to unseen synthesis methods and diverse sp…