Skip to main content
SpringerLink
Log in

Exploring ASR Models in Low-Resource Languages: Use-Case the Macedonian Language

  • Conference paper
  • First Online:
Deep Learning Theory and Applications (DeLTA 2023)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1875))

Included in the following conference series:

  • 438 Accesses

Abstract

We explore the use of Wav2Vec 2.0, NeMo, and ESPNet models trained on a dataset in Macedonian language for the development of Automatic Speech Recognition (ASR) models for low-resource languages. The study aims to evaluate the performance of recent state-of-the-art models for speech recognition in low-resource languages, such as Macedonian, where there are limited resources available for training or fine-tuning. The paper presents a methodology used for data collection and preprocessing, as well as the details of the three architectures used in the study. The study evaluates the performance of each model using WER and CER metrics and provides a comparative analysis of the results. The findings of the research showed that Wav2Vec 2.0 outperformed the other models for the Macedonian language with a WER of 0.21, and CER of 0.09, however, NeMo and ESPNet models are still good candidates for creating ASR tools for low-resource languages such as Macedonian. The research presented provides insights into the effectiveness of different models for ASR in low-resource languages and highlights the potentials for using these models to develop ASR tools for other languages in the future. These findings have significant implications for the development of ASR tools for other low-resource languages in the future, and can potentially improve accessibility to speech recognition technology for individuals and communities who speak these languages.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 69.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 89.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: Wav2vec 2.0: a framework for self-supervised learning of speech representations. Adv. Neural Inf. Process. Syst. 33, 12449–12460 (2020)

    Google Scholar 

  2. Bogdanoski, K., Mishev, K., Trajanov, D.: Blanket clusterer: a tool for automating the clustering in unsupervised learning (2022)

    Google Scholar 

  3. Dekker, R.: The importance of having data-sets (2006)

    Google Scholar 

  4. Developers, T.: Tensorflow. Zenodo (2021)

    Google Scholar 

  5. Dong, Q., et al.: Listen, understand and translate: triple supervision decouples end-to-end speech-to-text translation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 12749–12759 (2021)

    Google Scholar 

  6. Hajič, J.: Disambiguation of rich inflection: computational morphology of Czech. Karolinum (2004)

    Google Scholar 

  7. Hoffmann, R., Shpilewsky, E., Lobanov, B.M., Ronzhin, A.L.: Development of multi-voice and multi-language text-to-speech (TTS) and speech-to-text (STT) conversion system (languages: Belorussian, Polish, Russian). In: 9th Conference Speech and Computer (2004)

    Google Scholar 

  8. Hrinchuk, O., et al.: Nvidia nemo offline speech translation systems for IWSLT 2022. In: Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022), pp. 225–231 (2022)

    Google Scholar 

  9. Kriman, S., et al.: QuartzNet: deep automatic speech recognition with 1D time-channel separable convolutions. In: ICASSP 2020–2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6124–6128. IEEE (2020)

    Google Scholar 

  10. Kuchaiev, O., et al.: NeMo: a toolkit for building AI applications using neural modules. arXiv preprint arXiv:1909.09577 (2019)

  11. Mi, C., Xie, L., Zhang, Y.: Improving data augmentation for low resource speech-to-text translation with diverse paraphrasing. Neural Netw. 148, 194–205 (2022)

    Article  Google Scholar 

  12. Mishev, K., Karovska Ristovska, A., Trajanov, D., Eftimov, T., Simjanoska, M.: MAKEDONKA: applied deep learning model for text-to-speech synthesis in Macedonian language. Appl. Sci. 10(19), 6882 (2020)

    Article  Google Scholar 

  13. Mitreska, M., Pavlov, T., Mishev, K., Simjanoska, M.: xAMR: Cross-lingual AMR end-to-end pipeline (2022)

    Google Scholar 

  14. Nouza, J.: Strategies for developing a real-time continuous speech recognition system for Czech language. In: Sojka, P., Kopeček, I., Pala, K. (eds.) TSD 2002. LNCS (LNAI), vol. 2448, pp. 189–196. Springer, Heidelberg (2002). https://doi.org/10.1007/3-540-46154-X_26

    Chapter  Google Scholar 

  15. Nouza, J., Drabkova, J.: Combining lexical and morphological knowledge in language model for inflectional (Czech) language. In: Seventh International Conference on Spoken Language Processing (2002)

    Google Scholar 

  16. Nouza, J., Safarik, R., Cerva, P.: ASR for south Slavic languages developed in almost automated way. In: INTERSPEECH, pp. 3868–3872 (2016)

    Google Scholar 

  17. Nouza, J., Zdansky, J., Cerva, P., Silovsky, J.: Challenges in speech processing of Slavic languages (case studies in speech recognition of Czech and Slovak). In: Esposito, A., Campbell, N., Vogel, C., Hussain, A., Nijholt, A. (eds.) Development of Multimodal Interfaces: Active Listening and Synchrony. LNCS, vol. 5967, pp. 225–241. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-12397-9_19

    Chapter  Google Scholar 

  18. Pytorch, A.D.I.: Pytorch (2018)

    Google Scholar 

  19. Reddy, B.R., Mahender, E.: Speech to text conversion using android platform. Int. J. Eng. Res. Appl. (IJERA) 3(1), 253–258 (2013)

    Google Scholar 

  20. Ronzhin, A.L., Karpov, A.A.: Implementation of morphemic analysis for Russian speech recognition. In: 9th Conference Speech and Computer (2004)

    Google Scholar 

  21. Schultz, T.: GlobalPhone: a multilingual speech and text database developed at Karlsruhe university. In: Seventh International Conference on Spoken Language Processing (2002)

    Google Scholar 

  22. Tamburini, F.: Playing with nemo for building an automatic speech recogniser for Italian. In: CLiC-it (2021)

    Google Scholar 

  23. Wang, Y., et al.: Tacotron: towards end-to-end speech synthesis. arXiv preprint arXiv:1703.10135 (2017)

  24. Watanabe, S., et al.: ESPNet: end-to-end speech processing toolkit. arXiv preprint arXiv:1804.00015 (2018)

  25. Yu, C., Chen, Y., Li, Y., Kang, M., Xu, S., Liu, X.: Cross-language end-to-end speech recognition research based on transfer learning for the low-resource Tujia language. Symmetry 11(2), 179 (2019)

    Article  Google Scholar 

  26. Yu, D., Deng, L.: Automatic Speech Recognition, vol. 1. Springer, Heidelbergt (2016). https://doi.org/10.1007/978-1-4471-5779-3

    Book  MATH  Google Scholar 

  27. Zhang, Y., et al.: Learning to speak fluently in a foreign language: multilingual speech synthesis and cross-language voice cloning. arXiv preprint arXiv:1907.04448 (2019)

Download references

Author information

Authors and Affiliations

  1. Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University, Rugjer Boshkovikj 16, Skopje, North Macedonia

    Konstantin Bogdanoski, Kostadin Mishev, Monika Simjanoska & Dimitar Trajanov

  2. iReason LLC, 3rd Macedonian Brigade 37, Skopje, North Macedonia

    Kostadin Mishev & Monika Simjanoska

Authors
  1. Konstantin Bogdanoski
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kostadin Mishev
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Monika Simjanoska
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Dimitar Trajanov
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Konstantin Bogdanoski .

Editor information

Editors and Affiliations

  1. Université de Tours, Tours, France

    Donatello Conte

  2. Instituto de Telecomunicações and University of Lisbon, Lisbon, Portugal

    Ana Fred

  3. Ford Motor Company, Commerce Township, MI, USA

    Oleg Gusikhin

  4. University of Naples Federico II, Naples, Italy

    Carlo Sansone

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Bogdanoski, K., Mishev, K., Simjanoska, M., Trajanov, D. (2023). Exploring ASR Models in Low-Resource Languages: Use-Case the Macedonian Language. In: Conte, D., Fred, A., Gusikhin, O., Sansone, C. (eds) Deep Learning Theory and Applications. DeLTA 2023. Communications in Computer and Information Science, vol 1875. Springer, Cham. https://doi.org/10.1007/978-3-031-39059-3_17

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-39059-3_17

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-39058-6

  • Online ISBN: 978-3-031-39059-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation