bookEnhanced direct speech-to-speech translation using self-supervised pre-training and data augmentation
Direct speech-to-speech translation (S2ST) models suffer from data scarcity issues as there exists l...
2022-01-01 00:00:00
ChenP.J.GuJ.WangC.PopuriS.PinoJ.AdiY.
bookHide and speak: Towards deep neural networks for speech steganography
… For instance, the secret message may convey the speaker identity, the sentiment of the ...
2019-02-07 00:00:00
KreukF.AdiY.RajB.SinghR.KeshetJ.