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 …

We present the Multilingual TEDx corpus, built to support speech recognition (ASR) and
speech translation (ST) research across many non-English source languages. The corpus is …

Five years after the first published proofs of concept, direct approaches to speech translation
(ST) are now competing with traditional cascade solutions. In light of this steady progress …

Having numerous potential applications and great impact, end-to-end speech translation
(ST) has long been treated as an independent task, failing to fully draw strength from the …

Over its three decade history, speech translation has experienced several shifts in its
primary research themes; moving from loosely coupled cascades of speech recognition and …

Encoder pre-training is promising in end-to-end Speech Translation (ST), given the fact that
speech-to-translation data is scarce. But ST encoders are not simple instances of Automatic …

An end-to-end speech-to-text translation (ST) takes audio in a source language and outputs
the text in a target language. Existing methods are limited by the amount of parallel corpus …

Multimodal machine translation involves drawing information from more than one modality,
based on the assumption that the additional modalities will contain useful alternative views …

Spoken language translation has recently witnessed a resurgence in popularity, thanks to
the development of end-to-end models and the creation of new corpora, such as Augmented …

One of the main challenges for end-to-end speech translation is data scarcity. We leverage
pseudo-labels generated from unlabeled audio by a cascade and an end-to-end speech …