Textless Direct Speech-to-Speech Translation with Discrete Speech Representation.

Xinjian Li Ye Jia Chung-Cheng Chiu

Published in: ICASSP (2023)

Keyphrases

speech recognition
speech signal
audio visual
text to speech
automatic speech recognition
data sets
speech synthesis
dialogue system
broadcast news
neural network
machine translation
genetic algorithm
translation invariant
speaker recognition
multi lingual
real time
spontaneous speech
endpoint detection