The study of the attention mechanism has sparked interest in many fields, such as language
modeling and machine translation. Although its patterns have been exploited to perform …

Simultaneous speech translation (SimulST) systems aim at generating their output with the
lowest possible latency, which is normally computed in terms of Average Lagging (AL). In …

Production deployments in complex systems require ML architectures to be highly efficient
and usable against multiple tasks. Particularly demanding are classification problems in …

This paper describes the FBK's participation in the Simultaneous Translation and Automatic
Subtitling tracks of the IWSLT 2023 Evaluation Campaign. Our submission focused on the …

El objetivo de esta investigación fue analizar la calidad del subtitulado en vivo
interlingüístico, mediante el reconocimiento de voz automático y la traducción automática …

Simultaneous speech translation (SimulST) is the task in which output generation has to be
performed on partial, incremental speech input. In recent years, SimulST has become …

Automatic translation tools have facilitated navigating multilingual contexts, by providing
accessible shortcuts for gathering, processing, and spreading information. As language …

Modern translation devices cannot achieve the expected accuracy as they cannot make up
the target text as original as the source text on either the cultural or linguistic level …

Simultaneous translation is online decoding to translates with only subsentence. The goal of
simultaneous translation research is to improve translation performance against delay. For …