LiMuSE: Lightweight Multi-Modal Speaker Extraction.

Qinghua Liu Yating Huang Yunzhe Hao Jiaming Xu Bo Xu

Published in: SLT (2022)

Keyphrases

multi modal
lightweight
audio visual
speaker verification
communication infrastructure
speech recognition
multi modality
image annotation
development environments
uni modal
wireless sensor networks
semantic concepts
automatic speech recognition
video search
fusing multiple