Login / Signup
REDAT: Accent-Invariant Representation for End-to-End ASR by Domain Adversarial Training with Relabeling.
Hu Hu
Xuesong Yang
Zeynab Raeesy
Jinxi Guo
Gökçe Keskin
Harish Arsikere
Ariya Rastrow
Andreas Stolcke
Roland Maas
Published in:
CoRR (2020)
Keyphrases
</>
end to end
invariant representation
speech recognition
automatic speech recognition
invariant representations
congestion control
selective attention
computer vision
training set
spatio temporal
denoising
image matching
affine transformation
training process
text localization and recognition