Direct speech-to-speech translation (S2ST), in which all components can be optimized
jointly, is advantageous over cascaded approaches to achieve fast inference with a …

Abstract Speech-to-Text (ST) translation pertains to the task of converting speech signals in
one language to text in another language. It finds its application in various domains, such as …

We investigate the emergent abilities of the recently proposed web-scale speech model
Whisper, by adapting it to unseen tasks with prompt engineering. We selected three tasks …

This paper presents Translatotron 3, a novel approach to unsupervised direct speech-to-
speech translation from monolingual speech-text datasets by combining masked …

Direct speech-to-speech translation (S2ST) is an attractive research topic with many
advantages compared to cascaded S2ST. However, direct S2ST suffers from the data …

Speech-to-Speech Translation (S2ST) models transform speech from one language to
another target language with the same linguistic information. S2ST is important for bridging …

Most of the speech translation models heavily rely on parallel data, which is hard to collect
especially for low-resource languages. To tackle this issue, we propose to build a cascaded …

Studies of speech-to-speech machine translation for Turkic languages are practically absent
due to the difficulties of creating parallel speech corpora for training neural models …

Simultaneous speech-to-speech translation (S2ST) holds the promise of breaking down
communication barriers and enabling fluid conversations across languages. However …

Recently, many Transformer-based models have been applied to end-to-end speech
translation because of their capability to model global dependencies. Position embedding is …