2 papers
cs.CV2025
VALLR-Pin: Uncertainty-Factorized Visual Speech Recognition for Mandarin with Pinyin Guidance
Chang Sun, Dongliang Xie, Wanpeng Xie +2
Visual speech recognition (VSR) aims to transcribe spoken content from silent lip-motion videos and is particularly challenging in Mandarin due to severe viseme ambiguity and perva…
cs.SD2024
X-CrossNet: A complex spectral mapping approach to target speaker extraction with cross attention speaker embedding fusion
Chang Sun, Bo Qin
Target speaker extraction (TSE) is a technique for isolating a target speaker's voice from mixed speech using auxiliary features associated with the target speaker. It is another a…