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
Gokce Keskin
Harish Arsikere
Ariya Rastrow
Andreas Stolcke
Roland Maas
Published in:
ICASSP (2021)
Keyphrases
</>
end to end
invariant representation
automatic speech recognition
speech recognition
invariant representations
affine transformation
congestion control
real time
spoken language
selective attention
computer vision
multiscale
training set
image data
image registration
training process