VisageSynTalk: Unseen Speaker Video-to-Speech Synthesis via Speech-Visage Feature Selection. (arXiv:2206.07458v1 [cs.CV])

Web: http://arxiv.org/abs/2206.07458

The goal of this work is to reconstruct speech from a silent talking face
video. Recent studies have shown impressive performance on synthesizing speech
from silent talking face videos. However, they have not explicitly considered
on varying identity characteristics of different speakers, which place a
challenge in the video-to-speech synthesis, and this becomes more critical in
unseen-speaker settings. Distinct from the previous methods, our approach is to
separate the speech content and the visage-style from a given silent talking
face …

arxiv cv feature feature selection speech video