Self-Supervised Representations Improve End-to-End Speech Translation
INTERSPEECH, pp. 1491-1495, 2020.
End-to-end speech-to-text translation can provide a simpler and smaller system but is facing the challenge of data scarcity. Pre-training methods can leverage unlabeled data and have been shown to be effective on data-scarce settings. In this work, we explore whether self-supervised pre-trained speech representations can benefit the spe...More
Full Text (Upload PDF)
PPT (Upload PPT)