{"ID":2857199,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.10329","arxiv_id":"2510.10329","title":"End-to-end Automatic Speech Recognition and Speech Translation: Integration of Speech Foundational Models and LLMs","abstract":"Speech Translation (ST) is a machine translation task that involves converting speech signals from one language to the corresponding text in another language; this task has two different approaches, namely the traditional cascade and the more recent end-to-end. This paper explores a combined end-to-end architecture of pre-trained speech encoders and Large Language Models (LLMs) for performing both Automatic Speech Recognition (ASR) and ST simultaneously. Experiments with the English-to-German language pair show that our best model not only can achieve better translation results than SeamlessM4T, a large foundational end-to-end, multi-modal translation model, but can also match the performance of a cascaded system with Whisper and NLLB, with up to a score gain of 8% in $\\text{COMET}^{\\text{DA}}_{22}$ metric.","short_abstract":"Speech Translation (ST) is a machine translation task that involves converting speech signals from one language to the corresponding text in another language; this task has two different approaches, namely the traditional cascade and the more recent end-to-end. This paper explores a combined end-to-end architecture of...","url_abs":"https://arxiv.org/abs/2510.10329","url_pdf":"https://arxiv.org/pdf/2510.10329v1","authors":"[\"Nam Luu\",\"Ondřej Bojar\"]","published":"2025-10-11T20:10:30Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}