Developing automatic speech recognition for Scottish Gaelic

Lucy Evans*, William Lamb, Mark Sinclair, Beatrice Alex

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper discusses our efforts to develop a full automatic speech recognition (ASR) system for Scottish Gaelic, starting froma point of limited resource. Building ASR technology is important for documenting and revitalising endangered languages;it enables existing resources to be enhanced with automatic subtitles and transcriptions, improves accessibility for users,and, in turn, encourages continued use of the language. In this paper, we explain the many difficulties faced when collecting minority language data for speech recognition. A novel cross-lingual approach to the alignment of training data is used to overcome one such difficulty, and in this way we demonstrate how majority language resources can bootstrap the development of lower-resourced language technology. We use the Kaldi speech recognition toolkit to develop several Gaelic ASR systems,and report a final WER of 26.30%. This is a 9.50% improvement on our original model.
Original languageEnglish
Title of host publicationProceedings of the 4th Celtic Language Technology Workshop at LREC 2022 (CLTW 4)
EditorsTheodorus Fransen, William Lamb, Delyth Prys
PublisherEuropean Language Resources Association (ELRA)
Pages110-120
Number of pages11
ISBN (Electronic)9791095546733
Publication statusPublished - 15 Jun 2022
EventThe 4th Celtic Language Technology Workshop at LREC 2022 - Marseille, France
Duration: 20 Jun 202220 Jun 2022
http://techiaith.bangor.ac.uk/celticlt/cltw/?lang=en

Workshop

WorkshopThe 4th Celtic Language Technology Workshop at LREC 2022
Abbreviated titleCLTW 2022
Country/TerritoryFrance
CityMarseille
Period20/06/2220/06/22
Internet address

Keywords

  • Scottish Gaelic
  • Automatic Speech Recongition
  • Low-Resource ASR
  • alignment

Fingerprint

Dive into the research topics of 'Developing automatic speech recognition for Scottish Gaelic'. Together they form a unique fingerprint.

Cite this