Boito, M.Z., Yusuf, B., Ondel, L. et al. (2 more authors) (2022) Unsupervised word segmentation from discrete speech units in low-resource settings. In: Melero, M., Sakti, S. and Soria, C., (eds.) Proceedings of the LREC 2022 Workshop of the 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages (SIGUL 2022). 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages (SIGUL 2022), 24-25 Jun 2022, Marseille, France. European Language Resources Association (ELRA) , pp. 1-9. ISBN 9791095546917
Abstract
Documenting languages helps to prevent the extinction of endangered dialects – many of which are otherwise expected to disappear by the end of the century. When documenting oral languages, unsupervised word segmentation (UWS) from speech is a useful, yet challenging, task. It consists in producing time-stamps for slicing utterances into smaller segments corresponding to words, being performed from phonetic transcriptions, or in the absence of these, from the output of unsupervised speech discretization models. These discretization models are trained using raw speech only, producing discrete speech units that can be applied for downstream (text-based) tasks. In this paper we compare five of these models: three Bayesian and two neural approaches, with regards to the exploitability of the produced units for UWS. For the UWS task, we experiment with two models, using as our target language the Mboshi (Bantu C25), an unwritten language from Congo-Brazzaville. Additionally, we report results for Finnish, Hungarian, Romanian and Russian in equally low-resource settings, using only 4 hours of speech. Our results suggest that neural models for speech discretization are difficult to exploit in our setting, and that it might be necessary to adapt them to limit sequence length. We obtain our best UWS results by using Bayesian models that produce high quality, yet compressed, discrete representations of the input speech signal.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Editors: |
|
Copyright, Publisher and Additional Information: | © 2022 European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0 (http://creativecommons.org/licenses/by-nc/4.0/). |
Keywords: | unsupervised word segmentation; speech discretization; acoustic unit discovery; low-resource settings |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Funding Information: | Funder Grant number Engineering and Physical Sciences Research Council EP/T02450X/1 |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 01 Sep 2022 13:12 |
Last Modified: | 01 Sep 2022 13:12 |
Published Version: | https://sigul-2022.ilc.cnr.it/ |
Status: | Published |
Publisher: | European Language Resources Association (ELRA) |
Refereed: | Yes |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:190379 |