The field of speech processing has undergone a transformative shift with the advent of deep
learning. The use of multiple processing layers has enabled the creation of models capable …

How to learn a better speech representation for end-to-end speech-to-text translation (ST)
with limited labeled data? Existing techniques often attempt to transfer powerful machine …

Recently, speech-to-text translation has attracted more and more attention and many studies
have emerged rapidly. In this paper, we present a comprehensive survey on direct speech …

How can we learn unified representations for spoken utterances and their written text?
Learning similar representations for semantically similar speech and text is important for …

The rapid development of single-modal pre-training has prompted researchers to pay more
attention to cross-modal pre-training methods. In this paper, we propose a unified-modal …

How to solve the data scarcity problem for end-to-end speech-to-text translation (ST)? It's
well known that data augmentation is an efficient method to improve performance for many …

Abstract End-to-end (E2E) speech-to-text translation (ST) often depends on pretraining its
encoder and/or decoder using source transcripts via speech recognition or text translation …

End-to-end speech translation (ST) is the task of translating speech signals in the source
language into text in the target language. As a cross-modal task, end-to-end ST is difficult to …

The gap between speech and text modalities is a major challenge in speech-to-text
translation (ST). Different methods have been proposed to reduce this gap, but most of them …

Joint speech-language training is challenging due to the large demand for training data and
GPU consumption, as well as the modality gap between speech and language. We present …