Distortion-Controlled Training for end-to-end Reverberant Speech Separation with Auxiliary Autoencoding Loss.

Yi Luo Cong Han Nima Mesgarani

Published in: SLT (2021)

Keyphrases

end to end
speech signal
rate allocation
admission control
hearing impaired
speech recognition
ad hoc networks
wireless ad hoc networks
error propagation
content delivery
congestion control
multipath
high bandwidth
computational complexity
scalable video