Abstract
The rapid development of speech recognition systems has motivated the community to work on accent classification, considerably improving the performance of these systems. However, only a few works or tools have focused on evaluating and analyzing in depth not only the accent but also the pronunciation level of a person when learning a non-native language. Our study aims to evaluate the pronunciation skills of non-native English speakers whose first language is Arabic, Chinese, Spanish, or French. We considered training a system to compute posterior probabilities of phonological classes from English native speakers and then evaluating whether it is possible to discriminate between native English speakers vs. non-native English speakers. Posteriors of each phonological class separately and also their combination are considered. Phonemes with low posterior results are used to give feedback to the speaker regarding which phonemes should be improved. The results suggest that it is possible to distinguish between each of the non-native languages and native English with accuracies between 67.6% and 80.6%. According to our observations, the most discriminant phonological classes are alveolar, lateral, velar, and front. Finally, the paper introduces a graphical way to interpret the results phoneme-by-phoneme, such that the speaker receives feedback about his/her pronunciation performance.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bachman, L., Palmer, A.: Language Assessment in Practice: Developing language Assessments and Justifying Their Use in the Real World. Oxford University Press, Oxford (2022)
Berjon, P., et al.: Analysis of French phonetic idiosyncrasies for accent recognition. Soft Comput. Lett. 100018 (2021)
Cernak, M., et al.: Characterisation of voice quality of Parkinson’s disease using differential phonological posterior features. Comput. Speech Lang. 46, 196–208 (2017)
Crystal, D., et al.: English as a Global Language. Cambridge University Press, Cambridge (2003)
Dai, Y.: An automatic pronunciation error detection and correction mechanism in English teaching based on an improved random forest model. J. Electr. Comput. Eng. (2022)
Garofolo, J.S.: Timit acoustic phonetic continuous speech corpus. Linguist. Data Consortium (1993)
Graham, C.: L1 identification from L2 speech using neural spectrogram analysis. In: Proceedings of Interspeech, pp. 3959–3963 (2021)
Huang, C., et al.: Accent issues in large vocabulary continuous speech recognition. Int. J. Speech Technol. 7, 141–153 (2004)
Huerta, E.: Fonética comparada, español-francés, francés como segunda lengua para hispanohablantes, los fonemas complicados (2013)
Jenne, S., Vu, N.T.: Multimodal articulation-based pronunciation error detection with spectrogram and acoustic features. In: Proceedings of Interspeech, pp. 3549–3553 (2019)
Jiao, Y., et al.: Interpretable phonological features for clinical applications. In: Proceedings of ICASSP, pp. 5045–5049. IEEE (2017)
Kim, E., et al.: Automatic pronunciation assessment using self-supervised speech representation learning. arXiv preprint arXiv:2204.03863 (2022)
Lesnichaia, M., et al.: Classification of accented English using CNN model trained on amplitude mel-spectrograms. In: Proceedings of Interspeech, pp. 3669–3673 (2022)
Millar Cerda, M.A.: Los arabismos en la lengua española (1998)
Ocal, A.P.: Fonética contrastiva español/alemán, español/inglés, aspañol/francés y su aplicación a la enseñanza de la pronunciación española (1997)
Schnoor, T.T., et al.: Automatic accentedness rating using deep neural networks. In: Proceedings of Meetings on Acoustics ASA, vol. 45, p. 060013. Acoustical Society of America (2021)
Singh, Y., et al.: Features of speech audio for accent recognition, pp. 1–6 (2020)
Vásquez-Correa, J.C., et al.: Phonet: a tool based on gated recurrent neural networks to extract phonological posteriors from speech. In: Proceedings of Interspeech, pp. 549–553 (2019)
Wang, H.Y.: Estudio fónico del chino mandarín y del español (2001)
Weinberger, S.: Speech accent archive. George Mason University. Retrieved (2015)
Weninger, F., et al.: Deep learning based mandarin accent identification for accent robust ASR. In: Proceedings of Interspeech, pp. 510–514 (2019)
Acknowledgment
This work received funding from UdeA grant # ES92210001 and CODI grant No. PI2023-58010, and PRG2017-15530.
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
Rios-Urrego, C.D., Escobar-Grisales, D., Moreno-Acevedo, S.A., Perez-Toro, P.A., Nöth, E., Orozco-Arroyave, J.R. (2023). Automatic Pronunciation Assessment of Non-native English Based on Phonological Analysis. In: Ekštein, K., Pártl, F., Konopík, M. (eds) Text, Speech, and Dialogue. TSD 2023. Lecture Notes in Computer Science(), vol 14102. Springer, Cham. https://doi.org/10.1007/978-3-031-40498-6_30
Download citation
DOI: https://doi.org/10.1007/978-3-031-40498-6_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-40497-9
Online ISBN: 978-3-031-40498-6
eBook Packages: Computer ScienceComputer Science (R0)