# GMU Systems for the IWSLT 2025 Low-Resource Speech Translation Shared Task

arXiv: https://arxiv.org/abs/2505.21781 · HTML: https://mlsanity.com/paper/2505.21781/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 20 references that are in the map.
- First posted on arXiv 27 May 2025.

## Builds on (most cited first, 11 of 11)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Beyond English-Centric Multilingual Machine Translation](https://mlsanity.com/paper/2010.11125/) (2020)
- [Unsupervised Cross-lingual Representation Learning for Speech Recognition](https://mlsanity.com/paper/2006.13979/) (2020)
- [Seamless: Multilingual Expressive and Streaming Speech Translation](https://mlsanity.com/paper/2312.05187/) (2023)
- [CCMatrix: Mining Billions of High-Quality Parallel Sentences on the WEB](https://mlsanity.com/paper/1911.04944/) (2019)
- [Pre-training for Speech Translation: CTC Meets Optimal Transport](https://mlsanity.com/paper/2301.11716/) (2023)
- [BIG-C: a Multimodal Multi-Purpose Dataset for Bemba](https://mlsanity.com/paper/2305.17202/) (2023)
- [Leveraging Synthetic Audio Data for End-to-End Low-Resource Speech Translation](https://mlsanity.com/paper/2406.17363/) (2024)
- [Huqariq: A Multilingual Speech Corpus of Native Languages of Peru for Speech Recognition](https://mlsanity.com/paper/2207.05498/) (2022)

## Built on by (most cited first, 1 of 1)

- [Automated Gradient-Driven Parameter Sharing for Low-Resource Multilingual Speech-to-Text Translation](https://mlsanity.com/paper/2603.25836/) (2026)

## Abstract (arXiv)

This paper describes the GMU systems for the IWSLT 2025 low-resource speech translation shared task. We trained systems for all language pairs, except for Levantine Arabic. We fine-tuned SeamlessM4T-v2 for automatic speech recognition (ASR), machine translation (MT), and end-to-end speech translation (E2E ST). The ASR and MT models are also used to form cascaded ST systems. Additionally, we explored various training paradigms for E2E ST fine-tuning, including direct E2E fine-tuning, multi-task training, and parameter initialization using components from fine-tuned ASR and/or MT models. Our results show that (1) direct E2E fine-tuning yields strong results; (2) initializing with a fine-tuned ASR encoder improves ST performance on languages SeamlessM4T-v2 has not been trained on; (3) multi-task training can be slightly helpful.