3 papers
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.IR2025
Alleviating LLM-based Generative Retrieval Hallucination in Alipay Search
Yedan Shen, Kaixin Wu, Yuechen Ding +6
Generative retrieval (GR) has revolutionized document retrieval with the advent of large language models (LLMs), and LLM-based GR is gradually being adopted by the industry. Despit…
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…