{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T08:51:01Z","timestamp":1781772661255,"version":"3.54.5"},"reference-count":30,"publisher":"China Science Publishing & Media Ltd.","issue":"2","content-domain":{"domain":["engine.scichina.com"],"crossmark-restriction":false},"short-container-title":["DI"],"published-print":{"date-parts":[[2026,6,1]]},"DOI":"10.3724\/2096-7004.di.2025.0112","type":"journal-article","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T07:06:07Z","timestamp":1758524767000},"page":"20250112","update-policy":"https:\/\/doi.org\/10.1360\/scp-crossmark-policy-page","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing End-to-end Multilingual Medical Speech Translation via Terminology Injection Mechanism"],"prefix":"10.3724","volume":"8","author":[{"given":"Shuanghong","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chong","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xia","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinlei","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ge","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhang","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yulong","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"2026","published-online":{"date-parts":[[2025,9,22]]},"reference":[{"key":"null","unstructured":"Ney H., \u201cSpeech translation: Coupling of recognition and translation,\u201d in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP). Phoenix, AZ, USA: IEEE, Mar 1999, pp. 517\u2013520."},{"key":"null","unstructured":"Xu C. et al., \u201cStacked acoustic-and-textual encoding: Integrating the pre-trained models into speech translation encoders,\u201d in Proc. 59th Annu. Meeting Assoc. Comput. Linguistics Int. Joint Conf. Natural Lang. Process. (ACL\/IJCNLP). Assoc. Comput. Linguistics, Aug 2021, pp. 2619\u20132630."},{"key":"null","unstructured":"Indurthi S., Chollampatt S., Agrawal R., and Turchi M., \u201cCLAD-ST: Contrastive learning with adversarial data for robust speech translation,\u201d in Proc. Conf. Empirical Methods Natural Lang. Process. (EMNLP). Singapore: Assoc. Comput. Linguistics, Dec 2023, pp. 9049\u20139056."},{"key":"null","unstructured":"Chen X., Zhang S., Bai Q., Chen K., and Nakamura S., \u201cLLaST: Improved end-to-end speech translation system leveraged by large language models,\u201d in Findings Assoc. Comput. Linguistics (ACL). Bangkok, Thailand: Assoc. Comput. Linguistics, Aug 2024, pp. 6976\u20136987."},{"key":"null","unstructured":"Ardila R. et al., \u201cCommon Voice: A massively-multilingual speech corpus,\u201d in Proc. 12th Lang. Resour. Eval. Conf. (LREC). Marseille, France: Eur. Lang. Resour. Assoc., May 2020, pp. 4218\u20134222."},{"key":"null","unstructured":"Gangi M. A. D., Cattoni R., Bentivogli L., Negri M., and Turchi M., \u201cMuST-C: A multilingual speech translation corpus,\u201d in Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Human Lang. Technol. (NAACL-HLT). Minneapolis, MN, USA: Assoc. Comput. Linguistics, Jun 2019, pp. 2012\u20132017."},{"key":"null","unstructured":"Le-Duc K. et al., \u201cMultiMed-ST: Large-scale many-to-many multilingual medical speech translation,\u201d in Proc. Conf. Empirical Methods Natural Lang. Process. (EMNLP). Assoc. Comput. Linguistics, 2025, pp. 11838\u201311963."},{"key":"null","unstructured":"Radford A., Kim J. W., Xu T., Brockman G., McLeavey C., and Sutskever I., \u201cRobust speech recognition via largescale weak supervision,\u201d in Proc. Int. Conf. Mach. Learn. (ICML). Honolulu, HI, USA: PMLR, Jul 2023, pp. 28492\u201328518."},{"key":"null","unstructured":"Barrault L. et al., \u201cSeamlessM4T: Massively multilingual & multimodal machine translation,\u201d arXiv:2308.11596, 2023."},{"key":"null","unstructured":"Du Z. et al., \u201cLauraGPT: Listen, attend, understand, and regenerate audio with GPT,\u201d arXiv:2310.04673, 2023."},{"key":"null","unstructured":"Chu Y. et al., \u201cQwen-Audio: Advancing universal audio understanding via unified large-scale audio-language models,\u201d arXiv:2311.07919, 2023."},{"key":"null","unstructured":"Nakamura S. et al., \u201cThe ATR multilingual speech-to-speech translation system,\u201d IEEE Trans. Audio, Speech, Lang. Process., vol. 14, no. 2, pp. 365\u2013376, 2006."},{"key":"null","unstructured":"Lam T. K., Schamoni S., and Riezler S., \u201cCascaded models with cyclic feedback for direct speech translation,\u201d in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP). Toronto, ON, Canada: IEEE, Jun 2021, pp. 7508\u20137512."},{"key":"null","unstructured":"Sperber M., Neubig G., Niehues J., and Waibel A., \u201cAttention-passing models for robust and data-efficient end-to-end speech translation,\u201d Trans. Assoc. Comput. Linguistics (TACL), vol. 7, pp. 313\u2013325, 2019."},{"key":"null","unstructured":"Ye R., Wang M., and Li L., \u201cCross-modal contrastive learning for speech translation,\u201d in Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Human Lang. Technol. (NAACL). Seattle, WA, USA: Assoc. Comput. Linguistics, Jul 2022, pp. 5099\u20135113."},{"key":"null","unstructured":"Wang C., Tang Y., Ma X., Wu A., Okhonko D., and Pino J. M., \u201cFairseq S2T: Fast speech-to-text modeling with fairseq,\u201d in Proc. Conf. Asia-Pac. Chapter Assoc. Comput. Linguistics Int. Joint Conf. Natural Lang. Process., Syst. Demonstrations (AACL\/IJCNLP). Suzhou, China: Assoc. Comput. Linguistics, Dec 2020, pp. 33\u201339."},{"key":"null","unstructured":"Ye R., Wang M., and Li L., \u201cEnd-to-end speech translation via cross-modal progressive training,\u201d in Proc. Annu. Conf. Int. Speech Commun. Assoc. (Interspeech). Brno, Czechia: ISCA, Aug 2021, pp. 2267\u20132271."},{"key":"null","unstructured":"Tang C. et al., \u201cSALMONN: Towards generic hearing abilities for large language models,\u201d in Proc. 12th Int. Conf. Learn. Representations (ICLR). Vienna, Austria: OpenReview.net, May 2024."},{"key":"null","unstructured":"Dinu G., Mathur P., Federico M., and Al-Onaizan Y., \u201cTraining neural machine translation to apply terminology constraints,\u201d in Proc. 57th Conf. Assoc. Comput. Linguistics (ACL). Florence, Italy: Assoc. Comput. Linguistics, Jul 2019, pp. 3063\u20133068."},{"key":"null","unstructured":"Achiam J. et al., \u201cGPT-4 technical report,\u201d arXiv preprint arXiv:2303.08774, 2023."},{"key":"null","unstructured":"Ye Q., Ahmed M., Pryzant R., and Khani F., \u201cPrompt engineering a prompt engineer,\u201d in Findings Assoc. Comput. Linguistics (ACL). Bangkok, Thailand: Assoc. Comput. Linguistics, Aug 2024, pp. 355\u2013385."},{"key":"null","unstructured":"Wu Y. and Hu G., \u201cExploring prompt engineering with GPT language models for document-level machine translation: Insights and findings,\u201d in Proc. Conf. Mach. Transl. (WMT). Singapore: Assoc. Comput. Linguistics, Dec 2023, pp. 166\u2013169."},{"key":"null","unstructured":"Papineni K., Roukos S., Ward T., and Zhu W., \u201cBLEU: A method for automatic evaluation of machine translation,\u201d in Proc. 40th Annu. Meeting Assoc. Comput. Linguistics (ACL). Philadelphia, PA, USA: ACL, Jul 2002, pp. 311\u2013318."},{"key":"null","unstructured":"Zhang T., Kishore V., Wu F., Weinberger K. Q., and Artzi Y., \u201cBERTScore: Evaluating text generation with BERT,\u201d in Proc. 8th Int. Conf. Learn. Representations (ICLR). Addis Ababa, Ethiopia: OpenReview.net, Apr 2020."},{"key":"null","unstructured":"Hu E. J. et al., \u201cLoRA: Low-rank adaptation of large language models,\u201d in Proc. 10th Int. Conf. Learn. Representations (ICLR). Virtual Event: OpenReview.net, Apr 2022."},{"key":"null","unstructured":"Dubey A. et al., \u201cThe LLaMA 3\u00a0herd of models,\u201d arXiv preprint arXiv:2407.21783, 2024."},{"key":"null","unstructured":"Tang Y. et al., \u201cMultilingual translation with extensible multilingual pretraining and finetuning,\u201d arXiv preprint arXiv:2008.00401, 2020."},{"key":"null","unstructured":"Liu Y. et al., \u201cMultilingual denoising pre-training for neural machine translation,\u201d Trans. Assoc. Comput. Linguistics (TACL), vol. 8, pp. 726\u2013742, 2020."},{"key":"null","unstructured":"Fan A. et al., \u201cBeyond english-centric multilingual machine translation,\u201d J. Mach. Learn. Res., vol. 22, no. 107, pp. 1\u201348, 2021."},{"key":"null","unstructured":"Yang A. et al., \u201cQwen2.5 technical report,\u201d arXiv preprint arXiv:2412.15115, 2024."}],"container-title":["Data Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.sciengine.com\/sci-open\/api\/v1\/open\/file\/pdf\/3A69F4E28C6D4133B9382227B8B11C50","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.sciengine.com\/doi\/10.3724\/2096-7004.di.2025.0112","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.sciengine.com\/sci-open\/api\/v1\/open\/file\/pdf\/3A69F4E28C6D4133B9382227B8B11C50","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T07:52:34Z","timestamp":1781769154000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.sciengine.com\/doi\/10.3724\/2096-7004.di.2025.0112"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,22]]},"references-count":30,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,9,22]]},"published-print":{"date-parts":[[2026,6,1]]}},"URL":"https:\/\/doi.org\/10.3724\/2096-7004.di.2025.0112","relation":{},"ISSN":["2096-7004"],"issn-type":[{"value":"2096-7004","type":"print"}],"subject":[],"published":{"date-parts":[[2025,9,22]]}}}