3 papers
eess.AS2026
From Objectives to Applications: Aligning Architectural Biases in Audio Self-Supervised Learning
Kele Xu, Yulu Fang, Boda Zhou +6
This paper examines audio self-supervised learning (SSL) through the alignment between pretraining objectives, architectural inductive biases, and downstream applications. Rather t…
cs.SD2025
MuteSwap: Visual-informed Silent Video Identity Conversion
Yifan Liu, Yu Fang, Zhouhan Lin
Conventional voice conversion modifies voice characteristics from a source speaker to a target speaker, relying on audio input from both sides. However, this process becomes infeas…
cs.SD2025
DiVISe: Direct Visual-Input Speech Synthesis Preserving Speaker Characteristics And Intelligibility
Yifan Liu, Yu Fang, Zhouhan Lin
Video-to-speech (V2S) synthesis, the task of generating speech directly from silent video input, is inherently more challenging than other speech synthesis tasks due to the need to…