Improving Luxembourgish Speech Recognition with Cross-Lingual Speech Representations

Le Minh Nguyen, Shekhar Nayak, Matt Coler

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

3 Downloads (Pure)

Abstract

Luxembourgish is a West Germanic language spoken by roughly 390,000 people, mainly in Luxembourg. It is one of Europe's under-described and under-resourced languages, not extensively investigated in the context of speech recognition. We explore the self-supervised multilingual learning of Luxembourgish speech representations for the speech recognition downstream task. We show that learning cross-lingual representations is essential for low-resourced languages such as Luxembourgish. Learning cross-lingual representations and rescoring the output transcriptions with language modelling while using only 4 hours of labelled speech achieves a word error rate of 15.1% and improves our Transfer Learning baseline model relatively by 33.1% and absolutely by 7.5%. Increasing the amount of labelled speech to 14 hours yields a significant performance gain resulting in a 9.3% word error rate.11Models and datasets are available at https://hugging£ace.co/lemswasabi

Original languageEnglish
Title of host publication2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages792-797
Number of pages6
ISBN (Electronic)979-8-3503-9690-4
ISBN (Print)979-8-3503-9691-1
DOIs
Publication statusPublished - 2023
Event2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Doha, Qatar
Duration: 9-Jan-202312-Jan-2023

Publication series

Name2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings

Conference

Conference2022 IEEE Spoken Language Technology Workshop, SLT 2022
Country/TerritoryQatar
CityDoha
Period09/01/202312/01/2023

Keywords

  • language modelling
  • Luxembourgish
  • multilingual speech recognition
  • under-resourced language
  • wav2vec 2.0 XLSR-53

Cite this