Joint Speech Transcription and Translation: Pseudo-Labeling with Out-of-Distribution Data

      Self-training has been shown to be helpful in addressing data scarcity for many domains, including vision, speech, and language. Specifically, self-training, or pseudo-labeling, labels unsupervised data and adds that to the training pool. In this work, we investigate and use pseudo-labeling for a recently proposed novel setup: joint transcription and translation of speech, which suffers from an absence of sufficient parallel data resources. We show that under such data-deficient circumstances, the unlabeled data can significantly vary in domain from the supervised data, which results in… Read More Apple Machine Learning Research 

​  


Posted

in

by

Tags:

Comments

Leave a Reply

Your email address will not be published. Required fields are marked *