End-to-end Speech Translation is hindered by a lack of available data resources. While
most of them are based on documents, a sentence-level version is available, which is …

This article describes recent improvements of SLTev, a tool for automatic evaluation of
machine translation, speech recognition and speech translation systems. The changes …

In natural language processing, much current research focuses on training larger and larger
models on more and more data. In this thesis, we argue that how data is represented can …

Simultaneous speech-to-text translation (SimulST) translates source-language speech into
target-language text concurrently with the speaker's speech, ensuring low latency for better …