End-to-end Automatic Speech Recognition and Speech Translation: Integration of Speech Foundational Models and LLMs

ACL ARR 2025 February Submission1338 Authors

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.

Paper Type: Short

Research Area: Machine Translation

Research Area Keywords: multimodality, speech translation

Contribution Types: NLP engineering experiment

Languages Studied: English, German

Submission Number: 1338