Abstract
The deepening international integration of Vietnam is open the occupation opportunity for more and more foreigners. The demand for learning Vietnamese, therefore, is rising. However, Vietnamese can be difficult to pronounce for some who just getting started due to its complex vowels and tone marks. A Computer-Assisted Pronunciation Training system can significantly improve the capability of pronouncing for learners. In particular, a mispronunciation model plays an important role in this type of system. While there is still a limited number of researches for Vietnamese, this research introduces a process to build the new mispronunciation detection for the language. Besides, comparing some of the current advanced techniques in this task such as Goodness of Pronunciation for scoring and deep neural network for classifying, a process to build the Vietnamese vowels - tones test set is also introduced to evaluate the performance of the system. The best performance of the proposed model achieved a 0.54 F1 score and 0.46 PCC score on the built test set. This is a reasonable result, compare with a 0.45 PCC score on another English test set.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Witt, S.M., Young, S.J.: Phone-level pronunciation scoring and assessment for interactive language learning. Speech Commun. 95–108 (2000)
Hu, W., Qian, Y., Soong, F., Wang, Y.: Improved mispronunciation detection with deep neural network trained acoustic models and transfer learning based logistic regression classifiers. Speech Commun. 154–166 (2015)
Pham, N.M., Vu, H.Q.: Acceleration in state of the art ASR applied to a Vietnamese transcription system. J. Comput. Sci. Cybern. 365–372 (2018)
Luong, H.T., Vu. H.Q.: A non-expert Kaldi recipe for {V}ietnamese speech recognition system. In: Proceedings of the Third International Workshop on Worldwide Language Service Infrastructure and Second Workshop on Open Infrastructures and Analysis Frameworks for Human Language Technologies WLSI/OIAF4HLT@COLING, pp. 51–55 (2016)
Su, B., Mao, S., Soong, F., Xia, Y., Tien, J., Wu, Z.: Improving pronunciation assessment via ordinal regression with anchored reference samples. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7748–7752 (2021)
Shi, J., Huo, N., Jin, Q.: Context-aware goodness of pronunciation for computer-assisted pronunciation training. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, vol. 2020-October (2020)
Korzekwa, D., Trueba, J.L., Zaporowski, S., Calamaro, S., Drugman, T., Kostek, B.: Mispronunciation detection in non-native (L2) English with uncertainty modeling. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2021)
Wang, Z., Zhang, J., Xie, Y.: L2 mispronunciation verification based on acoustic phone embedding and Siamese networks. In: Proceedings of the 2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP), pp. 444–448 (2018)
Snyder, D., Chen, G., Povey, D.: MUSAN: a music, speech, and noise corpus. ArXiv (2015)
Zhang, J., et al.: Speechocean762: an open-source non-native English speech corpus for pronunciation assessment. ArXiv (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Minh, N.Q., Hung, P.D. (2021). The System for Detecting Vietnamese Mispronunciation. In: Dang, T.K., Küng, J., Chung, T.M., Takizawa, M. (eds) Future Data and Security Engineering. Big Data, Security and Privacy, Smart City and Industry 4.0 Applications. FDSE 2021. Communications in Computer and Information Science, vol 1500. Springer, Singapore. https://doi.org/10.1007/978-981-16-8062-5_32
Download citation
DOI: https://doi.org/10.1007/978-981-16-8062-5_32
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-8061-8
Online ISBN: 978-981-16-8062-5
eBook Packages: Computer ScienceComputer Science (R0)