On-device audio-visual multi-person wake word spotting.

Yidi Li Guoquan Wang Zhan Chen Hao Tang Hong Liu

Published in: CAAI Trans. Intell. Technol. (2023)

Keyphrases

audio visual
word spotting
multi modal
text processing
document images
dynamic time warping
visual information
visual data
optical character recognition
multi stream
multimedia
handwriting recognition
handwritten documents
computer vision
feature extraction
word level