Login / Signup
CCSRD: Content-Centric Speech Representation Disentanglement Learning for End-to-End Speech Translation.
Xiaohu Zhao
Haoran Sun
Yikun Lei
Shaolin Zhu
Deyi Xiong
Published in:
EMNLP (Findings) (2023)
Keyphrases
</>
end to end
speech recognition
content delivery
speech signal
rate allocation
admission control
multimedia
high bandwidth