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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
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)
Bogdanoski, K., Mishev, K., Trajanov, D.: Blanket clusterer: a tool for automating the clustering in unsupervised learning (2022)
Dekker, R.: The importance of having data-sets (2006)
Developers, T.: Tensorflow. Zenodo (2021)
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)
Hajič, J.: Disambiguation of rich inflection: computational morphology of Czech. Karolinum (2004)
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)
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)
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)
Kuchaiev, O., et al.: NeMo: a toolkit for building AI applications using neural modules. arXiv preprint arXiv:1909.09577 (2019)
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)
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)
Mitreska, M., Pavlov, T., Mishev, K., Simjanoska, M.: xAMR: Cross-lingual AMR end-to-end pipeline (2022)
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
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)
Nouza, J., Safarik, R., Cerva, P.: ASR for south Slavic languages developed in almost automated way. In: INTERSPEECH, pp. 3868–3872 (2016)
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
Pytorch, A.D.I.: Pytorch (2018)
Reddy, B.R., Mahender, E.: Speech to text conversion using android platform. Int. J. Eng. Res. Appl. (IJERA) 3(1), 253–258 (2013)
Ronzhin, A.L., Karpov, A.A.: Implementation of morphemic analysis for Russian speech recognition. In: 9th Conference Speech and Computer (2004)
Schultz, T.: GlobalPhone: a multilingual speech and text database developed at Karlsruhe university. In: Seventh International Conference on Spoken Language Processing (2002)
Tamburini, F.: Playing with nemo for building an automatic speech recogniser for Italian. In: CLiC-it (2021)
Wang, Y., et al.: Tacotron: towards end-to-end speech synthesis. arXiv preprint arXiv:1703.10135 (2017)
Watanabe, S., et al.: ESPNet: end-to-end speech processing toolkit. arXiv preprint arXiv:1804.00015 (2018)
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)
Yu, D., Deng, L.: Automatic Speech Recognition, vol. 1. Springer, Heidelbergt (2016). https://doi.org/10.1007/978-1-4471-5779-3
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)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
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)