The SETU-DCU Submissions to IWSLT 2024 Low-Resource Speech-to-Text Translation Tasks

Maria Zafar, Antonio Castaldo, Neha Gajakos, Prashanth Nayak, Rejwanul Haque, Andy Way

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

Natural Language Processing (NLP) research and development has experienced rapid progression in the recent times due to advances in deep learning. The introduction of pre-trained large language models (LLMs) is at the core of this transformation, significantly enhancing the performance of machine translation (MT) and speech technologies. This development has also led to fundamental changes in modern translation and speech tools and their methodologies. However, there remain challenges when extending this progress to underrepresented dialects and low-resource languages, primarily due to the need for more data.

Original languageEnglish
Title of host publicationIWSLT 2024 - 21st International Conference on Spoken Language Translation, Proceedings of the Conference
EditorsElizabeth Salesky, Marcello Federico, Marine Carpuat
PublisherAssociation for Computational Linguistics (ACL)
Pages128-133
Number of pages6
ISBN (Electronic)9798891761414
Publication statusPublished - 23 Sep 2024
Event21st International Conference on Spoken Language Translation, IWSLT 2024 - Hybrid, Bangkok, Thailand
Duration: 15 Apr 202416 Apr 2024

Publication series

NameIWSLT 2024 - 21st International Conference on Spoken Language Translation, Proceedings of the Conference

Conference

Conference21st International Conference on Spoken Language Translation, IWSLT 2024
Country/TerritoryThailand
CityHybrid, Bangkok
Period15/04/202416/04/2024

Fingerprint

Dive into the research topics of 'The SETU-DCU Submissions to IWSLT 2024 Low-Resource Speech-to-Text Translation Tasks'. Together they form a unique fingerprint.

Cite this