# KIT's Low-resource Speech Translation Systems for IWSLT2025: System Enhancement with Synthetic Data and Model Regularization

arXiv: https://arxiv.org/abs/2505.19679 · HTML: https://mlsanity.com/paper/2505.19679/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 23 references that are in the map.
- First posted on arXiv 26 May 2025.

## Builds on (most cited first, 10 of 10)

- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [R-Drop: Regularized Dropout for Neural Networks](https://mlsanity.com/paper/2106.14448/) (2021)
- [Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis](https://mlsanity.com/paper/2306.00814/) (2023)
- [Towards Robust Speech Representation Learning for Thousands of Languages](https://mlsanity.com/paper/2407.00837/) (2024)
- [Recipes for Adapting Pre-trained Monolingual and Multilingual Models to Machine Translation](https://mlsanity.com/paper/2004.14911/) (2020)
- [Leveraging Synthetic Audio Data for End-to-End Low-Resource Speech Translation](https://mlsanity.com/paper/2406.17363/) (2024)
- [When Is TTS Augmentation Through a Pivot Language Useful?](https://mlsanity.com/paper/2207.09889/) (2022)
- [The Importance of Being Parameters: An Intra-Distillation Method for Serious Gains](https://mlsanity.com/paper/2205.11416/) (2022)

## Built on by (most cited first, 3 of 3)

- [Multimodal In-context Learning for ASR of Low-resource Languages](https://mlsanity.com/paper/2601.05707/) (2026)
- [MUSCAT: MUltilingual, SCientific ConversATion Benchmark](https://mlsanity.com/paper/2604.15929/) (2026)
- [MLLP-VRAIN UPV system for the IWSLT 2026 Simultaneous Speech Translation task](https://mlsanity.com/paper/2606.17255/) (2026)

## Abstract (arXiv)

This paper presents KIT's submissions to the IWSLT 2025 low-resource track. We develop both cascaded systems, consisting of Automatic Speech Recognition (ASR) and Machine Translation (MT) models, and end-to-end (E2E) Speech Translation (ST) systems for three language pairs: Bemba, North Levantine Arabic, and Tunisian Arabic into English. Building upon pre-trained models, we fine-tune our systems with different strategies to utilize resources efficiently. This study further explores system enhancement with synthetic data and model regularization. Specifically, we investigate MT-augmented ST by generating translations from ASR data using MT models. For North Levantine, which lacks parallel ST training data, a system trained solely on synthetic data slightly surpasses the cascaded system trained on real data. We also explore augmentation using text-to-speech models by generating synthetic speech from MT data, demonstrating the benefits of synthetic data in improving both ASR and ST performance for Bemba. Additionally, we apply intra-distillation to enhance model performance. Our experiments show that this approach consistently improves results across ASR, MT, and ST tasks, as well as across different pre-trained models. Finally, we apply Minimum Bayes Risk decoding to combine the cascaded and end-to-end systems, achieving an improvement of approximately 1.5 BLEU points.