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: CoRR (2021)

Keyphrases

end to end
multi stream
scalable video
audio visual speech recognition
audio visual
admission control
automatic speech recognition
congestion control
hidden markov models
internet protocol
real world
computer vision
speech recognition
data fusion
signal to noise ratio