Two-Stage Augmentation and Adaptive CTC Fusion for Improved Robustness of Multi-Stream end-to-end ASR.

Ruizhi Li Gregory Sell Hynek Hermansky

Published in: SLT (2021)

Keyphrases

end to end
multi stream
scalable video
audio visual speech recognition
audio visual
congestion control
admission control
multi modal
automatic speech recognition
information fusion
data fusion
internet protocol
transport layer
noisy environments
application layer
contextual information
high dimensional