Please use this identifier to cite or link to this item:
https://www.um.edu.mt/library/oar/handle/123456789/114771| Title: | UM-DFKI Maltese speech translation |
| Authors: | Williams, Aiden Abela, Kurt Kumar, Rishu Bär, Martin Billinghurst, Hannah Micallef, Kurt Mozib Samin, Ahnaf DeMarco, Andrea van der Plas, Lonneke Borg, Claudia |
| Keywords: | Automatic speech recognition -- Malta Translating and interpreting -- Technological innovations Speech processing systems Translating services |
| Issue Date: | 2023 |
| Publisher: | Association for Computational Linguistics |
| Citation: | Williams, A., Abela, K., Kumar, R., Bär, M., Billinghurt, H., Micallef, K.,…Borg, C. (2023). Findings Of the IWSLT 2023 Evaluation Campaign. 20th International Conference on Spoken Language Translation (IWSLT 2023), Toronto. 433-441. |
| Abstract: | For the 2023 IWSLT Maltese Speech Translation Task, UM-DFKI jointly presents a cascade solution which achieves 0.6 BLEU. While this is the first time that a Maltese speech translation task has been released by IWSLT, this paper explores previous solutions for other speech translation tasks, focusing primarily on low-resource scenarios. Moreover, we present our method of fine-tuning XLS-R models for Maltese ASR using a collection of multi-lingual speech corpora as well as the fine-tuning of the mBART model for Maltese to English machine translation. |
| URI: | https://www.um.edu.mt/library/oar/handle/123456789/114771 |
| Appears in Collections: | Scholarly Works - FacICTAI |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 2023.iwslt-1.41.pdf | 177.79 kB | Adobe PDF | View/Open |
Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.