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 …

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) is a demanding task that involves generating
translations in real-time while continuously processing speech input. This paper offers a …

Attention is the core mechanism of today's most used architectures for natural language
processing and has been analyzed from many perspectives, including its effectiveness for …

The primary goal of this FBK's systems submission to the IWSLT 2022 offline and
simultaneous speech translation tasks is to reduce model training costs without sacrificing …

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 …

A popular approach to streaming speech translation is to employ a single offline model with
a wait-k policy to support different latency requirements, which is simpler than training …

As a robust and large-scale multilingual speech recognition model, Whisper has
demonstrated impressive results in many low-resource and out-of-distribution scenarios …

Pre-trained speech models, such as wav2vec 2.0, have significantly advanced speech-
related tasks, including speech recognition and translation. However, their applicability in …

Recent work in speech-to-speech translation (S2ST) has focused primarily on offline
settings, where the full input utterance is available before any output is given. This, however …