Large-scale automatic speech translation systems today lack key features that help machine-
mediated communication feel seamless when compared to human-to-human dialogue. In …

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 …

This paper reports on the shared tasks organized by the 20th IWSLT Conference. The
shared tasks address 9 scientific challenges in spoken language translation: simultaneous …

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 …

Decoder-only large language models (LLMs) have recently demonstrated impressive
capabilities in text generation and reasoning. Nonetheless, they have limited applications in …

Transducer and Attention based Encoder-Decoder (AED) are two widely used frameworks
for speech-to-text tasks. They are designed for different purposes and each has its own …

In real-world applications, users often require both translations and transcriptions of speech
to enhance their comprehension, particularly in streaming scenarios where incremental …

Large language models (LLM) have demonstrated their abilities to solve various natural
language processing tasks through dialogue-based interactions. For instance, research …

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 …

Blockwise self-attentional encoder models have recently emerged as one promising end-to-
end approach to simultaneous speech translation. These models employ a blockwise beam …