CLJan 25, 2025

Speech Translation Refinement using Large Language Models

arXiv:2501.15090v11 citationsh-index: 4Has Code
Originality Incremental advance
AI Analysis

This work addresses the problem of enhancing speech translation accuracy for users in multilingual communication, presenting an incremental improvement by applying LLMs to existing refinement methods.

The paper tackled improving speech translation performance by using large language models (LLMs) to jointly refine speech translation and automatic speech recognition transcriptions, resulting in significant gains across multiple datasets and translation tasks.

Recent advancements in large language models (LLMs) have demonstrated their remarkable capabilities across various language tasks. Inspired by the success of text-to-text translation refinement, this paper investigates how LLMs can improve the performance of speech translation by introducing a joint refinement process. Through the joint refinement of speech translation (ST) and automatic speech recognition (ASR) transcription via LLMs, the performance of the ST model is significantly improved in both training-free in-context learning and parameter-efficient fine-tuning scenarios. Additionally, we explore the effect of document-level context on refinement under the context-aware fine-tuning scenario. Experimental results on the MuST-C and CoVoST 2 datasets, which include seven translation tasks, demonstrate the effectiveness of the proposed approach using several popular LLMs including GPT-3.5-turbo, LLaMA3-8B, and Mistral-12B. Further analysis further suggests that jointly refining both transcription and translation yields better performance compared to refining translation alone. Meanwhile, incorporating document-level context significantly enhances refinement performance. We release our code and datasets on GitHub.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes