KIT's Low-resource Speech Translation Systems for IWSLT2025: System Enhancement with Synthetic Data and Model Regularization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918309506580480 |
|---|---|
| author | Li, Zhaolin Liu, Yining Liu, Danni Nguyen, Tuan Nam Ugan, Enes Yavuz Dinh, Tu Anh Mullov, Carlos Waibel, Alexander Niehues, Jan |
| author_facet | Li, Zhaolin Liu, Yining Liu, Danni Nguyen, Tuan Nam Ugan, Enes Yavuz Dinh, Tu Anh Mullov, Carlos Waibel, Alexander Niehues, Jan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_19679 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | KIT's Low-resource Speech Translation Systems for IWSLT2025: System Enhancement with Synthetic Data and Model Regularization Li, Zhaolin Liu, Yining Liu, Danni Nguyen, Tuan Nam Ugan, Enes Yavuz Dinh, Tu Anh Mullov, Carlos Waibel, Alexander Niehues, Jan Computation and Language Artificial Intelligence 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. |
| title | KIT's Low-resource Speech Translation Systems for IWSLT2025: System Enhancement with Synthetic Data and Model Regularization |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2505.19679 |