Abstract
Phonetic transcription is an approach to represent speech sounds to specific symbols. The most common alphabet we used is the International Phonetic Alphabet (IPA), and the characters in the IPA are phonetic symbols. To support the phonetic transcription process in the phonetic exams of our linguistic E-learning system, we designed a machine translation tool that aims to translate English words to their phonetic formats. This progress can also be expressed as grapheme to phoneme (G2P). The Transformer model has been utilized to develop this G2P module. Also, to improve the functionality of the E-learning system, we trained multiple language models and generated a multilingual G2P translator. Moreover, we evaluated our G2P system by word error rate (WER) and phoneme error rate (PER) with edit distance.
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
Similar content being viewed by others
References
Reuge, N., et al.: Education response to COVID 19 pandemic, a special issue proposed by UNICEF: editorial review. Int. J. Educ. Dev. 87, 102485 (2021)
Nichols, M.: A theory for eLearning. J. Educ. Technol. Soc. 6(2), 1–10 (2003)
Seals, C.D., et al.: Applied webservices platform supported through modified edit distance algorithm: automated phonetic transcription grading tool (APTgt). In: Zaphiris, P., Ioannou, A. (eds.) HCII 2020. LNCS, vol. 12205, pp. 380–398. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-50513-4_29
Liu, J., et al.: Optimization to automated phonetic transcription grading tool (APTgt) – automatic exam generator. In: Zaphiris, P., Ioannou, A. (eds.) HCII 2021. LNCS, vol. 12784, pp. 80–91. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-77889-7_6
Brown, A.: International Phonetic Alphabet. The Encyclopedia of Applied Linguistics (2012)
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)
Bisani, M., Ney, H.: Joint-sequence models for grapheme-to-phoneme conversion. Speech Commun. 50(5), 434–451 (2008)
Klakow, D., Peters, J.: Testing the correlation of word error rate and perplexity. Speech Commun. 38(1–2), 19–28 (2002)
Taylor, P.: Hidden Markov models for grapheme to phoneme conversion. In: Ninth European Conference on Speech Communication and Technology (2005)
Rao, K., et al.: Grapheme-to-phoneme conversion using long short-term memory recurrent neural networks. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2015)
Yang, S., Wang, Y., Chu, X.: A survey of deep learning techniques for neural machine translation. arXiv preprint arXiv:2002.07526 (2020)
Kominek, J., Black, A.W.: The CMU arctic speech databases. In: Fifth ISCA Workshop on Speech Synthesis (2004)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, J. et al. (2022). Transformer-Based Multilingual G2P Converter for E-Learning System. In: Degen, H., Ntoa, S. (eds) Artificial Intelligence in HCI. HCII 2022. Lecture Notes in Computer Science(), vol 13336. Springer, Cham. https://doi.org/10.1007/978-3-031-05643-7_35
Download citation
DOI: https://doi.org/10.1007/978-3-031-05643-7_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-05642-0
Online ISBN: 978-3-031-05643-7
eBook Packages: Computer ScienceComputer Science (R0)