Assessing Neural Machine Translation in Speech: Problems and Solutions in AI-Powered Translations
DOI:
https://doi.org/10.64472/jciet.v2i1.27Keywords:
AI-assisted Translation, Neural Machine Translation, Speech Translation, Translation ProblemsAbstract
The swift progress of artificial intelligence (AI), particularly in Neural Machine Translation (NMT) systems, has substantially transformed the landscape of translation practices. While AI-powered applications such as Monica AI (Powered by ChatGPT) demonstrate a high degree of linguistic accuracy, there remains a notable research gap regarding the specific translation challenges encountered by professional translators when working with AI-generated outputs, especially in speech texts. The theoretical novelty of this study lies in integrating Nord’s text-typological translation problem framework with Molina and Albir’s translation technique model to evaluate NMT output, an approach rarely applied to spoken oratory texts. Empirically, the study provides a fine-grained error analysis of a ChatGPT-powered NMT system on formal political speech, quantifying problem types and mapping them to specific post-editing strategies. Utilizing a qualitative content analysis approach, this research examines a formal English-language speech text translated using Monica AI. A total of 282 source sentences, along with their AI-generated and post-edited versions, served as the corpus. Findings reveal that 91.1% of the translated sentences were accurate, while 8.9% contained identifiable issues, predominantly within pragmatic, conventional, and text-specific domains. This study emphasizes the indispensable role of human translators in ensuring cultural and contextual appropriateness in AI-assisted translation.
Downloads
References
[1] C. M. Ionașcu, “Artificial Intelligence Adoption in the European Union: A Data-Driven Cluster Analysis (2021–2024),” 2025. doi: https://doi.org/10.3390/economies13050145.
[2] Z. Li, “Artificial Intelligence Machine Translation Based on Fuzzy Algorithm,” Mob. Inf. Syst., vol. 2021, no. 1, p. 1827627, Jan. 2021, doi: https://doi.org/10.1155/2021/1827627
[3] Q. Ai, Q. Ai, and J. Wang, “Exploration on advanced intelligent algorithms of artificial intelligence for verb recognition in machine translation,” ACM Trans. Asian Low-resour. Lang. Inf. Process., vol. 23, no. 8, pp. 1–18, 2024, doi: https://doi.org/10.1145/3649891
[4] P. Armenteros-Cosme, M. Arias-González, S. Alonso-Rollán, S. Márquez-Sánchez, and A. Carrera, “Advancements in Artificial Intelligence and Machine Learning for Occupational Risk Prevention: A Systematic Review on Predictive Risk Modeling and Prevention Strategies,” 2025. doi: https://doi.org/10.3390/s25175419
[5] W. Zhu, L. Wei, and Y. Qin, “Artificial Intelligence in Education (AIEd): Publication Patterns, Keywords, and Research Focuses,” 2025. doi: https://doi.org/10.3390/info16090725
[6] T. Kim, D. Agarwal, J. Ackerman, and M. Saha, “Steering AI-driven personalization of scientific text for general audiences,” Proc. ACM Hum. Comput. Interact., vol. 9, no. 7, pp. 1–28, 2025, doi: https://doi.org/10.1145/3757660
[7] P. Sánchez-Gijón, “What experts say about increasingly relevant translation technologies,” Tradumàtica tecnol. trad., no. 20, pp. 295–301, 2022, doi: https://doi.org/10.5565/rev/tradumatica.322
[8] Z. Yang et al., “ShennongAlpha: an AI-driven sharing and collaboration platform for intelligent curation, acquisition, and translation of natural medicinal material knowledge,” Cell Discov., vol. 11, no. 1, p. 32, 2025, doi: https://doi.org/10.1038/s41421-025-00776-2
[9] Y. Wang, “Enhancing english oral translation through cross-modal learning and synchronous optimization,” PLoS One, vol. 20, no. 8, p. e0329381, 2025, doi: https://doi.org/10.1371/journal.pone.0329381
[10] V. Berisha and J. M. Liss, “Responsible development of clinical speech AI: Bridging the gap between clinical research and technology,” npj Digit. Med., vol. 7, no. 1, 2024, doi: https://doi.org/10.1038/s41746-024-01199-1
[11] P. Polakova and B. Klimova, “Using DeepL translator in learning English as an applied foreign language – An empirical pilot study,” Heliyon, vol. 9, no. 8, p. e18595, 2023, doi: https://doi.org/10.1016/j.heliyon.2023.e18595
[12] T. Alqahtani et al., “The emergent role of artificial intelligence, natural learning processing, and large language models in higher education and research,” 2023. doi: https://doi.org/10.1016/j.sapharm.2023.05.016
[13] Y. Wang, “Artificial Intelligence Technologies in College English Translation Teaching,” J. Psycholinguist. Res., vol. 52, no. 5, pp. 1525–1544, 2023, doi: https://doi.org/10.1007/s10936-023-09960-5
[14] H. Xu, A. Woicik, H. Poon, R. B. Altman, and S. Wang, “Multilingual translation for zero-shot biomedical classification using BioTranslator,” Nat. Commun., vol. 14, no. 1, 2023, doi: https://doi.org/10.1038/s41467-023-36476-2
[15] L. W. Y. Yang et al., “Development and testing of a multi-lingual Natural Language Processing-based deep learning system in 10 languages for COVID-19 pandemic crisis: A multi-center study,” Front. Public Heal., vol. 11, 2023, doi: https://doi.org/10.3389/fpubh.2023.1063466
[16] M. T. Krause, C. Nord, and P. Sparrow, Text Analysis in Translation: Theory, Methodology, and Didactic Application of a Model for Translation-Oriented Text Analysis, vol. 76, no. 4. Rodopi, 1992. doi: https://doi.org/10.2307/330103
[17] L. Molina and A. H. Albir, “Translation techniques revisited: A dynamic and functionalist approach,” Meta, vol. 47, no. 4, pp. 498–512, 2002, doi: https://doi.org/10.7202/008033ar
[18] K. Krippendorff, Content Analysis: An Introduction to Its Methodology. Sage publications, 2022. doi: https://doi.org/10.4135/9781071878781
[19] W. Untara and T. Setiawan, “PROBLEMA MESIN PENERJEMAH BERBASIS AI DALAM PROSES PENERJEMAHAN BUKU INGGRIS-INDONESIA DAN SOLUSINYA,” Adab. J. Bhs. Dan Sastra, vol. 4, no. 1, pp. 92–115, 2020, doi: https://doi.org/10.14421/ajbs.2020.04105
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Ahmad Zaki Munibi (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
PROPOSED POLICY FOR JOURNALS OFFERING OPEN ACCESS
The following conditions must be fulfilled by the Authors:
-
Copyright and Licensing
Authors retain copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal. -
Non-Exclusive Distribution
Authors may enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., posting it to an institutional repository or publishing it in a book), with an acknowledgment of its initial publication in this journal. -
Online Posting and Early Sharing
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their personal websites) prior to and during the submission process, as this can lead to productive exchanges, as well as earlier and increased citation of the published work. (See The Effect of Open Access).
