Gerard I. Gállego

SHAS: Approaching optimal Segmentation for End-to-End Speech Translation

2022 · arXiv (Cornell University)

Speech translation models are unable to directly process long audios, like TED talks, which have to be split into shorter segments. Speech translation datasets provide manual segmentations of the audios, which are not available in …

Efficient Speech Translation with Dynamic Latent Perceivers

2023

Transformers have been the dominant architecture for Speech Translation in recent years, achieving significant improvements in translation quality. Since speech signals are longer than their textual counterparts, and due to the quadratic complexity of the …