Audio-Visual Multi-person Keyword Spotting via Hybrid Fusion.

Yuxin Su Ziling Miao Hong Liu

Published in: CICAI (2) (2022)

Keyphrases

audio visual
keyword spotting
person authentication
multimodal fusion
multi modal
speech recognition
visual information
hidden markov models
printed documents
multi stream
multimedia
visual data
speech processing
audio features
image content
automatic speech recognition
pattern recognition