# LLaST: Improved End-to-end Speech Translation System Leveraged by Large Language Models

Source: [LLaST: Improved End-to-end Speech Translation System Leveraged by Large Language Models](<https://www.sota2.com/research/paper/68fa742d1e209131cea603ff>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:03:52.408Z

Authors: Xi Chen, Songyang Zhang, Qibing Bai, Kai Chen, Satoshi Nakamura

Published: 2024-07-22T06:42:00.000Z

## Abstract

We introduces LLaST, a framework for building high-performance Large Language model based Speech-to-text Translation systems. We address the limitations of end-to-end speech translation(E2E ST) models by exploring model architecture design and optimization techniques tailored for LLMs. Our approach includes LLM-based speech translation architecture design, ASR-augmented training, multilingual data augmentation, and dual-LoRA optimization. Our approach demonstrates superior performance on the CoVoST-2 benchmark and showcases exceptional scaling capabilities powered by LLMs. We believe this effective method will serve as a strong baseline for speech translation and provide insights for future improvements of the LLM-based speech translation framework. We release the data, code and models in https://github.com/openaudiolab/LLaST.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Speech Translation on NTUML Monolingual 2021 (test)](<https://www.sota2.com/research/sota/speech-translation-on-ntuml-monolingual-2021-test.md>): Speech Translation; NTUML Monolingual 2021 (test); BLEU: 33.81.

- [Speech Translation on Fisher Code-Switching (test)](<https://www.sota2.com/research/sota/speech-translation-on-fisher-code-switching-test.md>): Speech Translation; Fisher Code-Switching (test); BLEU: 33.78.

- [Speech Translation on Fisher Monolingual (test)](<https://www.sota2.com/research/sota/speech-translation-on-fisher-monolingual-test.md>): Speech Translation; Fisher Monolingual (test); BLEU: 30.67.

- [Speech Translation on NTUML Code-Switching 2021 (test)](<https://www.sota2.com/research/sota/speech-translation-on-ntuml-code-switching-2021-test.md>): Speech Translation; NTUML Code-Switching 2021 (test); BLEU: 32.53.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2407.15415>)

[PDF](<https://arxiv.org/pdf/2407.15415.pdf>)