Cross-attention is a core mechanism in encoder-decoder architectures, widespread in many fields, including speech-to-text (S2T) processing. Its scores have been repurposed for various downstream appli...

Simultaneous speech-to-text translation systems must balance translation quality with latency. Although quality evaluation is well established, latency measurement remains a challenge. Existing metric...

Speech Large Language Models (SLLMs) have rapidly expanded, supporting a wide range of tasks. These models are typically evaluated using text prompts, which may not reflect real-world scenarios where ...

Unlike text, speech conveys information about the speaker, such as gender, through acoustic cues like pitch. This gives rise to modality-specific bias concerns. For example, in speech translation (ST)...

This link will take you to a page that’s not on LinkedIn

Home of the IWSLT conference and SIGSLT.

Home of the IWSLT conference and SIGSLT.

Home of the IWSLT conference and SIGSLT.

The most powerful, simple and trusted way to gather experience data. Start your journey to experience management and try a free account today.

ALT: a polar bear cub is laying in a pile of branches .