AI-Based Intelligent Document Translator And Audio Reader For Telugu Language
DOI:
https://doi.org/10.63503/acset.978-81-995593-9-4.54Keywords:
Machine Translation, Natural Language Processing, Telugu; Post-Editing, Document Translation, Synthesis Speech.Abstract
Accurate machine translation for low-resource languages remains a significant challenge, particularly for technical documents where consistent terminology is essential. This work presents a dictionary-guided post-editing framework for English-to-Telugu document translation. The proposed system operates as a lightweight post-processing layer applied after translation and does not require modifications to the underlying translation model or additional training data. Terminology consistency is achieved through semantic matching with a curated Telugu glossary, ensuring uniform translation of domain-specific terms across the entire document. The system is evaluated using standard translation quality metrics and demonstrates improved performance compared to existing large-scale translation systems. The proposed method achieves a score of 9.23 on a widely used evaluation metric and 42.00 on a character-based evaluation measure, showing consistent improvement in both lexical and morphological accuracy. In addition, a speech synthesis module is integrated to convert translated text into audio form, enhancing accessibility for users. The results indicate that the proposed framework provides a practical and scalable solution for improving translation quality in low-resource language settings, particularly for technical and domain-specific content.
References
[1] T. O. Tafa et al., ”Machine Translation Performance for Low-Resource Languages: A Systematic Literature Review,” in IEEE Access, vol. 13, pp. 72486-72505, 2025.
[2] Hendy, M. Abdelrehim, A. Sharaf, V. Raunak, M. Gabr, H. Matsushita, Y. J. Kim, M. Afify, and H. Hassan Awadalla, ”How good are GPT models at machine translation? A comprehensive A evaluation,” 2023.
[3] H. Moon, C. Park, S. Eo, J. Seo and H. Lim, ”An Empirical Study on Automatic Post Editing for Neural Machine Translation,” in IEEE Access, vol. 9, pp. 123754-123763, 2021, doi: 10.1109/ACCESS.2021.
[4] L. Zhu et al., ”Document-Level Neural Machine Translation With Document Embeddings,” in IEEE Access, vol. 13, pp. 87015-87025, 2025.
[5] M. Karpinska and M. Iyyer, “Large language models effectively leverage document-level context for literary translation, but critical errors persist,” in Proc. 8th Conf. Mach. Transl., 2023.
[6] K. Zhong, J. Zhang, and W. Guo, “Document-level machine translation with effective batch-level context representation,” in Proc. Int. Joint Conf. Neural Netw. (IJCNN), Jun. 2024.
[7] X. -D. Doan, V. -H. Vu, N. -D. Nguyen and V. -T. Tran, ”Document-Level Machine Translation with Context-Aware Memory,” 2024 16th International Conference on Knowledge and System Engineering (KSE), Kuala Lumpur, Malaysia, 2024.
[8] L. Cagliero and M. L. Quatra, ”Inferring Multilingual Domain-Specific Word Embeddings From Large Document Corpora,” in IEEE Access, vol. 9, pp. 137309-137321, 2021.
[9] S. Zhu, L. Pan, D. Jian, and D. Xiong, “Overcoming language barriers via machine translation with sparse mixture-of-experts fusion of large language models,” Inf. Process. Manage, vol. 62, no. 3, May 2025.
[10] Y. Wang, J. Zhang, T. Shi, D. Deng, Y. Tian and T. Matsumoto, ”Recent Advances in Interactive Machine Translation With Large Language Models,” in IEEE Access, vol. 12, pp. 179353-179382, 2024.
[11] A. Jha, H. Y. Patil, S. K. Jindal and S. M. N. Islam, ”Multilingual Indian Language Neural Machine Translation System Using mT5 Transformer,” 2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS), Nagpur, India, 2023.
[12] M. Asmitha and C. R. Kavitha, ”Bridging the Language Gap: Enhancing English-to-Telugu Translation using NMT and Encoding Decoding Techniques,” 2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT), Kamand, India, 2024.
[13] B. V. Sai Abhishek, K. Yamuna and T. Anjali, ”Multilingual Translational Optical Character Recognition System for Printed Telugu Text,” 2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT), Kharagpur, India, 2021.
[14] A. Latif and J. Kim, ”Evaluation and Analysis of Large Language Models for Clinical Text Augmentation and Generation,” in IEEE Access, vol. 12, pp. 48987-48996, 2024.
[15] Y. Du, Y. -F. Ma, Z. Xie and M. Li, ”Beyond Lexical Consistency: Preserving Semantic Consistency for Program Translation,” 2023 IEEE International Conference on Data Mining (ICDM), Shanghai, China, 2023.
[16] Ramesh Saini, ”Enhancing Indian Language Translation Using Machine Learning: A Comprehensive Approach”, 2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), pp.1-5, 2023.
