VE-KWS: Visual Modality Enhanced End-to-End Keyword Spotting.

Ao Zhang He Wang Pengcheng Guo Yihui Fu Lei Xie Yingying Gao Shilei Zhang Junlan Feng

Published in: ICASSP (2023)

Keyphrases

end to end
keyword spotting
multi modal
speech recognition
speech processing
congestion control
hidden markov models
printed documents
admission control
visual information
neural network
visual features
text classification
feature vectors
image retrieval
digital libraries
bayesian networks
real time