{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T22:23:39Z","timestamp":1793485419498,"version":"4.5.0"},"reference-count":136,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci\u00f3n","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100016386","name":"Government of Valencia Ministry of Innovation Universities Science and Society","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100016386","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100020655","name":"European Health and Digital Executive Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100020655","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Artificial Intelligence in Medicine"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1016\/j.artmed.2025.103147","type":"journal-article","created":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T15:46:37Z","timestamp":1747237597000},"page":"103147","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":12,"special_numbering":"C","title":["Speech translation for multilingual medical education leveraged by large language models"],"prefix":"10.1016","volume":"166","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7414-9600","authenticated-orcid":false,"given":"Jorge","family":"Iranzo-S\u00e1nchez","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4335-7418","authenticated-orcid":false,"given":"Jaume","family":"Santamar\u00eda-Jord\u00e0","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7688-5746","authenticated-orcid":false,"given":"Gerard","family":"Mas-Moll\u00e0","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2594-5858","authenticated-orcid":false,"given":"Gon\u00e7al V. Garc\u00e9s","family":"D\u00edaz-Mun\u00edo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Javier","family":"Iranzo-S\u00e1nchez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Javier","family":"Jorge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2291-8296","authenticated-orcid":false,"given":"Joan Albert","family":"Silvestre-Cerd\u00e0","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adri\u00e0","family":"Gim\u00e9nez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0963-0143","authenticated-orcid":false,"given":"Jorge","family":"Civera","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2943-0990","authenticated-orcid":false,"given":"Albert","family":"Sanchis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9984-4072","authenticated-orcid":false,"given":"Alfons","family":"Juan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.artmed.2025.103147_b1","article-title":"Attention is all you need","volume":"vol. 30","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.artmed.2025.103147_b2","series-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"10.1016\/j.artmed.2025.103147_b3","series-title":"Findings of the association for computational linguistics","first-page":"11127","article-title":"Steering large language models for machine translation with finetuning and in-context learning","author":"Alves","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b4","series-title":"Proceedings of the 2023 conference on empirical methods in natural language processing","first-page":"12567","article-title":"Multilingual large language models are not (yet) code-switchers","author":"Zhang","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b5","series-title":"EONS cancer nursing index 2020 - education and career development","author":"EONS Advocacy Working Group","year":"2020"},{"key":"10.1016\/j.artmed.2025.103147_b6","series-title":"GPT-4 technical report","author":"OpenA","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b7","unstructured":"Hendy A, Abdelrehim MG, Sharaf A, Raunak V, Gabr M, Matsushita H, et al. How Good Are GPT Models at Machine Translation?. A Compr Eval arXiv abs\/2302.09210. https:\/\/arxiv.org\/abs\/2302.09210."},{"key":"10.1016\/j.artmed.2025.103147_b8","series-title":"Proceedings of the eighth conference on machine translation","first-page":"1","article-title":"Findings of the 2023 conference on machine translation (WMT23): LLMs are here but not quite there yet","author":"Kocmi","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b9","series-title":"Proceedings of the eighth conference on machine translation","first-page":"43","article-title":"Findings of the WMT 2023 biomedical translation shared task: Evaluation of ChatGPT 3.5 as a comparison system","author":"Neves","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.csl.2023.101582","article-title":"Adopting machine translation in the healthcare sector: A methodological multi-criteria review","volume":"84","author":"Zappatore","year":"2024","journal-title":"Comput Speech Lang"},{"key":"10.1016\/j.artmed.2025.103147_b11","series-title":"Proceedings of the eighth conference on machine translation","first-page":"271","article-title":"The path to continuous domain adaptation improvements by HW-TSC for the WMT23 biomedical translation shared task","author":"Wu","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b12","series-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b13","series-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b14","series-title":"The Falcon series of open language models","author":"Almazrouei","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b15","unstructured":"Zhao WX, Zhou K, Li J, Tang T, Wang X, Hou Y et al. A survey of large language models. CoRR abs\/2303.18223. arXiv:2303.18223. http:\/\/dx.doi.org\/10.48550\/arXiv.2303.18223."},{"key":"10.1016\/j.artmed.2025.103147_b16","series-title":"A survey for in-context learning","author":"Dong","year":"2022"},{"key":"10.1016\/j.artmed.2025.103147_b17","series-title":"Advances in neural information processing systems 33: annual conference on neural information processing systems 2020","first-page":"6","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"10.1016\/j.artmed.2025.103147_b18","series-title":"Proceedings of the 61st annual meeting of the association for computational linguistics (volume 1: long papers)","first-page":"15406","author":"Vilar","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b19","series-title":"Findings of the association for computational linguistics","first-page":"2606","article-title":"Controlling styles in neural machine translation with activation prompt","author":"Wang","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b20","article-title":"Emergent abilities of large language models","author":"Wei","year":"2022","journal-title":"Trans Mach Learn Res 2022"},{"key":"10.1016\/j.artmed.2025.103147_b21","first-page":"55565","article-title":"Are emergent abilities of large language models a mirage?","volume":"vol. 36","author":"Schaeffer","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b22","series-title":"Proceedings of the 2021 conference on empirical methods in natural language processing","first-page":"5915","article-title":"Data and parameter scaling laws for neural machine translation","author":"Gordon","year":"2021"},{"key":"10.1016\/j.artmed.2025.103147_b23","series-title":"The tenth international conference on learning representations","first-page":"25","article-title":"Scaling laws for neural machine translation","author":"Ghorbani","year":"2022"},{"key":"10.1016\/j.artmed.2025.103147_b24","series-title":"Scaling laws for multilingual neural machine translation","author":"Fernandes","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b25","series-title":"Proceedings of the 40th international conference on machine learning","article-title":"Transformers learn in-context by gradient descent","author":"Von Oswald","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b26","series-title":"Findings of the association for computational linguistics","first-page":"4005","article-title":"Why can GPT learn in-context? language models secretly perform gradient descent as meta-optimizers","author":"Dai","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b27","series-title":"Proceedings of the eleventh international conference on learning representations","article-title":"What learning algorithm is in-context learning? Investigations with linear models","author":"Aky\u00fcrek","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b28","series-title":"An empirical study of catastrophic forgetting in large language models during continual fine-tuning","author":"Luo","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b29","series-title":"Proceedings of the 36th international conference on machine learning, 97 of proceedings of machine learning research","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","author":"Houlsby","year":"2019"},{"key":"10.1016\/j.artmed.2025.103147_b30","series-title":"International conference on learning representations","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2022"},{"key":"10.1016\/j.artmed.2025.103147_b31","series-title":"International conference on learning representations","article-title":"Measuring the intrinsic dimension of objective landscapes","author":"Li","year":"2018"},{"key":"10.1016\/j.artmed.2025.103147_b32","series-title":"Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing (volume 1: long papers)","first-page":"7319","article-title":"Intrinsic dimensionality explains the effectiveness of language model fine-tuning","author":"Aghajanyan","year":"2021"},{"key":"10.1016\/j.artmed.2025.103147_b33","series-title":"Multilingual machine translation with large language models: Empirical results and analysis","author":"Zhu","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b34","series-title":"How good are GPT models at machine translation? A comprehensive evaluation","author":"Hendy","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b35","series-title":"Proceedings of the 24th annual conference of the European association for machine translation","first-page":"157","article-title":"Investigating the translation performance of a large multilingual language model: the case of BLOOM","author":"Bawden","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b36","series-title":"Eliciting the translation ability of large language models via multilingual finetuning with translation instructions","author":"Li","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b37","series-title":"Proceedings of the 40th international conference on machine learning","article-title":"Prompting large language model for machine translation: a case study","author":"Zhang","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b38","unstructured":"Garc\u00eda X, Bansal Y, Cherry C, Foster GF, Krikun M, Feng F, et al. The unreasonable effectiveness of few-shot learning for machine translation. In: Proceedings of the eleventh international conference on learning representations. OpenReview.net https:\/\/openreview.net\/pdf?id=zvCSNsoyKW."},{"key":"10.1016\/j.artmed.2025.103147_b39","series-title":"Proceedings of the 61st annual meeting of the association for computational linguistics (volume 2: short papers)","first-page":"1041","article-title":"Do GPTs produce less literal translations?","author":"Raunak","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b40","doi-asserted-by":"crossref","first-page":"1500","DOI":"10.1162\/tacl_a_00615","article-title":"Hallucinations in large multilingual translation models","volume":"11","author":"Guerreiro","year":"2023","journal-title":"Trans Assoc Comput Linguist"},{"key":"10.1016\/j.artmed.2025.103147_b41","series-title":"Proceedings of the 40th annual meeting on association for computational linguistics","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"Papineni","year":"2002"},{"key":"10.1016\/j.artmed.2025.103147_b42","series-title":"Proceedings of the 2020 conference on empirical methods in natural language processing","first-page":"2685","article-title":"COMET: A neural framework for MT evaluation","author":"Rei","year":"2020"},{"key":"10.1016\/j.artmed.2025.103147_b43","series-title":"Proceedings of the seventh conference on machine translation","first-page":"578","article-title":"COMET-22: Unbabel-IST 2022 submission for the metrics shared task","author":"Rei","year":"2022"},{"key":"10.1016\/j.artmed.2025.103147_b44","series-title":"Proceedings of the sixth conference on machine translation","first-page":"478","article-title":"To ship or not to ship: An extensive evaluation of automatic metrics for machine translation","author":"Kocmi","year":"2021"},{"key":"10.1016\/j.artmed.2025.103147_b45","series-title":"Proc. of interspeech","first-page":"2625","article-title":"Sequence-to-sequence models can directly translate Foreign speech","author":"Weiss","year":"2017"},{"key":"10.1016\/j.artmed.2025.103147_b46","series-title":"2018 IEEE international conference on acoustics, speech and signal processing","first-page":"6224","article-title":"End-to-end automatic speech translation of audiobooks","author":"B\u00e9rard","year":"2018"},{"key":"10.1016\/j.artmed.2025.103147_b47","series-title":"Proceedings of machine translation summit XVII: research track","first-page":"21","article-title":"Enhancing transformer for end-to-end speech-to-text translation","author":"Gangi","year":"2019"},{"key":"10.1016\/j.artmed.2025.103147_b48","series-title":"Proc. of interspeech","first-page":"1123","article-title":"Direct speech-to-speech translation with a sequence-to-sequence model","author":"Jia","year":"2019"},{"key":"10.1016\/j.artmed.2025.103147_b49","series-title":"Proceedings of the 20th international conference on spoken language translation","first-page":"1","article-title":"Findings of the iwslt 2023 evaluation campaign","author":"Agarwal","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b50","series-title":"Proceedings of the 21st international conference on spoken language translation","first-page":"1","article-title":"Findings of the iwslt 2024 evaluation campaign","author":"Ahmad","year":"2024"},{"key":"10.1016\/j.artmed.2025.103147_b51","series-title":"Proc. interspeech 2020","first-page":"5036","article-title":"Conformer: Convolution-augmented transformer for speech recognition","author":"Gulati","year":"2020"},{"key":"10.1016\/j.artmed.2025.103147_b52","series-title":"Proceedings of the 21st international conference on spoken language translation","first-page":"235","article-title":"Recent highlights in multilingual and multimodal speech translation","author":"Liu","year":"2024"},{"key":"10.1016\/j.artmed.2025.103147_b53","series-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022"},{"key":"10.1016\/j.artmed.2025.103147_b54","series-title":"Seamless: Multilingual expressive and streaming speech translation","author":"Seamless Communication","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b55","series-title":"NeurIPS","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020"},{"key":"10.1016\/j.artmed.2025.103147_b56","unstructured":"Costa-juss\u00e0 MR, Cross J, \u00c7elebi O, Elbayad M, Heafield K, Heffernan K et al. No language left behind: Scaling human-centered machine translation, CoRR abs\/2207.04672. https:\/\/arxiv.org\/abs\/2207.04672."},{"key":"10.1016\/j.artmed.2025.103147_b57","series-title":"Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 1: long papers)","first-page":"14760","article-title":"Speech translation with speech foundation models and large language models: What is there and what is missing?","author":"Gaido","year":"2024"},{"key":"10.1016\/j.artmed.2025.103147_b58","series-title":"INTERSPEECH","first-page":"3974","article-title":"Alignatt: Using attention-based audio-translation alignments as a guide for simultaneous speech translation","author":"Papi","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b59","series-title":"Proceedings of the 13th international joint conference on natural language processing and the 3rd conference of the Asia-Pacific chapter of the association for computational linguistics: system demonstrations","first-page":"17","article-title":"Turning whisper into real-time transcription system","author":"Mach\u00e1\u010dek","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b60","series-title":"Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 1: long papers)","first-page":"3692","article-title":"StreamAtt: Direct streaming speech-to-text translation with attention-based audio history selection","author":"Papi","year":"2024"},{"key":"10.1016\/j.artmed.2025.103147_b61","series-title":"Proceedings of the 21st international conference on spoken language translation","first-page":"183","article-title":"Blending LLMs into cascaded speech translation: KIT\u2019s offline speech translation system for IWSLT 2024","author":"Koneru","year":"2024"},{"key":"10.1016\/j.artmed.2025.103147_b62","series-title":"Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 1: long papers)","first-page":"10530","article-title":"Simul-LLM: A framework for exploring high-quality simultaneous translation with large language models","author":"Agostinelli","year":"2024"},{"key":"10.1016\/j.artmed.2025.103147_b63","doi-asserted-by":"crossref","unstructured":"Deng K, Woodland P. Label-Synchronous Neural Transducer for E2E Simultaneous Speech Translation. In: Ku L-W, Martins A, Eds. V Srikumar, editors. Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 1: long papers). Association for Computational Linguistics; p. 8235\u201351. http:\/\/dx.doi.org\/10.18653\/v1\/2024.acl-long.448, URL https:\/\/aclanthology.org\/2024.acl-long.448.","DOI":"10.18653\/v1\/2024.acl-long.448"},{"key":"10.1016\/j.artmed.2025.103147_b64","doi-asserted-by":"crossref","unstructured":"Guo S, Zhang S, Feng Y. Decoder-only Streaming Transformer for Simultaneous Translation. In: Ku L-W, Martins A, Srikumar V, editors. Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 1: long papers). Association for Computational Linguistics; p. 8851\u201364. http:\/\/dx.doi.org\/10.18653\/v1\/2024.acl-long.480, URL https:\/\/aclanthology.org\/2024.acl-long.480.","DOI":"10.18653\/v1\/2024.acl-long.480"},{"issue":"9","key":"10.1016\/j.artmed.2025.103147_b65","doi-asserted-by":"crossref","DOI":"10.1016\/j.ejso.2023.106989","article-title":"An inter-specialty cancer training programme curriculum for Europe","volume":"49","author":"Benstead","year":"2023","journal-title":"Eur J Surg Oncol"},{"key":"10.1016\/j.artmed.2025.103147_b66","series-title":"NAACL-HLT (1)","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.artmed.2025.103147_b67","article-title":"Links between markov models and multilayer perceptrons","volume":"vol. 1","author":"Bourlard","year":"1988"},{"key":"10.1016\/j.artmed.2025.103147_b68","series-title":"Proc. interspeech 2019","first-page":"3820","article-title":"Real-time one-pass decoder for speech recognition using LSTM language models","author":"Jorge","year":"2019"},{"key":"10.1016\/j.artmed.2025.103147_b69","series-title":"ICASSP 2020-2020 IEEE international conference on acoustics, speech and signal processing","first-page":"7814","article-title":"Lstm-based one-pass decoder for low-latency streaming","author":"Jorge","year":"2020"},{"key":"10.1016\/j.artmed.2025.103147_b70","series-title":"Advances in speech and language technologies for iberian languages","first-page":"269","article-title":"The translectures-UPV Toolkit","author":"del Agua","year":"2014"},{"key":"10.1016\/j.artmed.2025.103147_b71","series-title":"2017 IEEE international conference on acoustics, speech and signal processing","first-page":"2462","article-title":"A comprehensive study of deep bidirectional LSTM RNNS for acoustic modeling in speech recognition","author":"Zeyer","year":"2017"},{"key":"10.1016\/j.artmed.2025.103147_b72","series-title":"Proc. interspeech 2019","first-page":"2613","article-title":"SpecAugment: A simple data augmentation method for automatic speech recognition","author":"Park","year":"2019"},{"key":"10.1016\/j.artmed.2025.103147_b73","series-title":"Proc. interspeech 2020","first-page":"2127","article-title":"Improved hybrid streaming ASR with transformer language models","author":"Baquero-Arnal","year":"2020"},{"key":"10.1016\/j.artmed.2025.103147_b74","series-title":"TensorFlow: Large-scale machine learning on heterogeneous systems, software available from tensorflow.org","author":"Abadi","year":"2015"},{"key":"10.1016\/j.artmed.2025.103147_b75","series-title":"Proceedings of the sixth workshop on statistical machine translation","first-page":"187","article-title":"KenLM: Faster and smaller language model queries","author":"Heafield","year":"2011"},{"key":"10.1016\/j.artmed.2025.103147_b76","series-title":"Proc. interspeech 2019","first-page":"3905","article-title":"Language modeling with deep transformers","author":"Irie","year":"2019"},{"key":"10.1016\/j.artmed.2025.103147_b77","series-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics (demonstrations)","first-page":"48","article-title":"fairseq: A fast, extensible toolkit for sequence modeling","author":"Ott","year":"2019"},{"key":"10.1016\/j.artmed.2025.103147_b78","doi-asserted-by":"crossref","unstructured":"Mart\u00ednez-Villaronga A, del Agua MA, Andr\u00e9s-Ferrer J, Juan A. Language model adaptation for video lectures transcription. In: 2013 IEEE international conference on acoustics, speech and signal processing. Vancouver (Canada; 2013, p. 8450\u20134. http:\/\/dx.doi.org\/10.1109\/ICASSP.2013.6639314, URL https:\/\/ieeexplore.ieee.org\/document\/6639314.","DOI":"10.1109\/ICASSP.2013.6639314"},{"key":"10.1016\/j.artmed.2025.103147_b79","series-title":"Artificial neural networks and machine learning","first-page":"270","article-title":"A survey on deep transfer learning","author":"Tan","year":"2018"},{"key":"10.1016\/j.artmed.2025.103147_b80","series-title":"Proceedings of the sixth conference on machine translation","first-page":"205","article-title":"Facebook AI\u2019s WMT21 news translation task submission","author":"Tran","year":"2021"},{"key":"10.1016\/j.artmed.2025.103147_b81","series-title":"Proceedings of the seventh conference on machine translation","first-page":"694","article-title":"Findings of the WMT 2022 biomedical translation shared task: Monolingual clinical case reports","author":"Neves","year":"2022"},{"key":"10.1016\/j.artmed.2025.103147_b82","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1016\/j.aiopen.2022.10.001","article-title":"A survey of transformers","volume":"3","author":"Lin","year":"2022","journal-title":"AI Open"},{"key":"10.1016\/j.artmed.2025.103147_b83","series-title":"When is multilinguality a curse? language modeling for 250 high- and low-resource languages","author":"Chang","year":"2023"},{"issue":"5","key":"10.1016\/j.artmed.2025.103147_b84","doi-asserted-by":"crossref","DOI":"10.1145\/3406095","article-title":"A survey of multilingual neural machine translation","volume":"53","author":"Dabre","year":"2020","journal-title":"ACM Comput Surv"},{"key":"10.1016\/j.artmed.2025.103147_b85","series-title":"Proceedings of the 2023 conference on empirical methods in natural language processing","first-page":"4895","article-title":"GQA: Training generalized multi-query transformer models from multi-head checkpoints","author":"Ainslie","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b86","series-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"10.1016\/j.artmed.2025.103147_b87","article-title":"Root mean square layer normalization","volume":"vol. 32","author":"Zhang","year":"2019"},{"key":"10.1016\/j.artmed.2025.103147_b88","series-title":"GLU variants improve transformer","author":"Shazeer","year":"2020"},{"key":"10.1016\/j.artmed.2025.103147_b89","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.127063","article-title":"RoFormer: Enhanced transformer with rotary position embedding","volume":"568","author":"Su","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.artmed.2025.103147_b90","unstructured":"Kew T, Schottmann F, Sennrich R. Turning English-centric LLMs Into Polyglots: How Much Multilinguality Is Needed?, arXiv:2312.12683. http:\/\/dx.doi.org\/10.48550\/arXiv.2312.12683."},{"key":"10.1016\/j.artmed.2025.103147_b91","series-title":"ICASSP 2020-2020 IEEE international conference on acoustics, speech and signal processing","first-page":"8229","article-title":"Europarl-ST: A multilingual corpus for speech translation of parliamentary debates","author":"Iranzo-S\u00e1nchez","year":"2020"},{"key":"10.1016\/j.artmed.2025.103147_b92","series-title":"Proc. of NAACL-HLT","first-page":"2012","article-title":"MuST-C: a multilingual speech translation corpus","author":"Di Gangi","year":"2019"},{"key":"10.1016\/j.artmed.2025.103147_b93","series-title":"Proceedings of the seventh conference on machine translation","first-page":"46","article-title":"Results of WMT22 metrics shared task: Stop using BLEU \u2013 neural metrics are better and more robust","author":"Freitag","year":"2022"},{"key":"10.1016\/j.artmed.2025.103147_b94","unstructured":"Graham Y, Baldwin T, Moffat A, Zobel J. Continuous Measurement Scales in Human Evaluation of Machine Translation. In: Pareja-Lora A, Liakata M, Dipper S, editors. Proceedings of the 7th linguistic annotation workshop and interoperability with discourse. Association for Computational Linguistics; p. 33\u201341, URL https:\/\/aclanthology.org\/W13-2305."},{"key":"10.1016\/j.artmed.2025.103147_b95","doi-asserted-by":"crossref","unstructured":"Lommel A, Uszkoreit H, Burchardt A. Multidimensional Quality Metrics (MQM): A Framework for Declaring and Describing Translation Quality Metrics 12 455\u2013463 http:\/\/dx.doi.org\/10.5565\/rev\/tradumatica.77. https:\/\/revistes.uab.cat\/tradumatica\/article\/view\/n12-lommel-uzskoreit-burchardt.","DOI":"10.5565\/rev\/tradumatica.77"},{"key":"10.1016\/j.artmed.2025.103147_b96","first-page":"I","article-title":"Bootstrap estimates for confidence intervals in asr performance evaluation","volume":"vol. 1","author":"Bisani","year":"2004"},{"key":"10.1016\/j.artmed.2025.103147_b97","series-title":"Statistical testing on asr performance via blockwise bootstrap","author":"Liu","year":"2020"},{"key":"10.1016\/j.artmed.2025.103147_b98","series-title":"Proceedings of the third conference on machine translation: research papers","first-page":"186","article-title":"A call for clarity in reporting BLEU scores","author":"Post","year":"2018"},{"key":"10.1016\/j.artmed.2025.103147_b99","series-title":"Proceedings of the 2004 conference on empirical methods in natural language processing","first-page":"388","article-title":"Statistical significance tests for machine translation evaluation","author":"Koehn","year":"2004"},{"key":"10.1016\/j.artmed.2025.103147_b100","series-title":"Proceedings of the ninth conference on machine translation","first-page":"1272","article-title":"Pitfalls and outlooks in using COMET","author":"Zouhar","year":"2024"},{"key":"10.1016\/j.artmed.2025.103147_b101","series-title":"Proceedings of the 19th international conference on spoken language translation","first-page":"1","article-title":"SubER - A metric for automatic evaluation of subtitle quality","author":"Wilken","year":"2022"},{"key":"10.1016\/j.artmed.2025.103147_b102","series-title":"Transllama: Llm-based simultaneous translation system","author":"Koshkin","year":"2024"},{"key":"10.1016\/j.artmed.2025.103147_b103","series-title":"Sillm: Large language models for simultaneous machine translation","author":"Guo","year":"2024"},{"key":"10.1016\/j.artmed.2025.103147_b104","series-title":"Simultaneous machine translation with large language models","author":"Wang","year":"2024"},{"key":"10.1016\/j.artmed.2025.103147_b105","doi-asserted-by":"crossref","first-page":"979","DOI":"10.1162\/tacl_a_00683","article-title":"xcomet: Transparent machine translation evaluation through fine-grained error detection","volume":"12","author":"Guerreiro","year":"2024","journal-title":"Trans Assoc Comput Linguist"},{"key":"10.1016\/j.artmed.2025.103147_b106","series-title":"2015 IEEE international conference on acoustics, speech and signal processing","first-page":"5206","article-title":"Librispeech: An asr corpus based on public domain audio books","author":"Panayotov","year":"2015"},{"key":"10.1016\/j.artmed.2025.103147_b107","series-title":"Proceedings of the ninth international conference on language resources and evaluation","first-page":"3935","article-title":"Enhancing the TED-LIUM corpus with selected data for language modeling and more TED talks","author":"Rousseau","year":"2014"},{"key":"10.1016\/j.artmed.2025.103147_b108","series-title":"Proceedings of the workshop on visually grounded interaction and language (viGIL), neurIPS","article-title":"How2: a large-scale dataset for multimodal language understanding","author":"Sanabria","year":"2018"},{"issue":"2","key":"10.1016\/j.artmed.2025.103147_b109","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s10579-017-9410-y","article-title":"The spoken wikipedia corpus collection: Harvesting, alignment and an application to hyperlistening","volume":"53","author":"Baumann","year":"2019","journal-title":"Lang Resour Eval"},{"key":"10.1016\/j.artmed.2025.103147_b110","unstructured":"VoxForge. http:\/\/www.voxforge.org\/."},{"key":"10.1016\/j.artmed.2025.103147_b111","series-title":"2015 IEEE workshop on automatic speech recognition and understanding","first-page":"504","article-title":"The third \u2018chime\u2019 speech separation and recognition challenge: Dataset, task and baselines","author":"Barker","year":"2015"},{"issue":"2","key":"10.1016\/j.artmed.2025.103147_b112","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1007\/s10579-007-9040-x","article-title":"Unleashing the killer corpus: experiences in creating the multi-everything AMI meeting corpus","volume":"41","author":"Carletta","year":"2007","journal-title":"Lang Resour Eval"},{"key":"10.1016\/j.artmed.2025.103147_b113","unstructured":"CSTR\u2019s VCTK Corpus. https:\/\/datashare.ed.ac.uk\/handle\/10283\/2950."},{"key":"10.1016\/j.artmed.2025.103147_b114","unstructured":"The ELFA Corpus. http:\/\/www.uta.fi\/ltl\/en\/english\/research\/projects\/elfa\/corpus.html."},{"key":"10.1016\/j.artmed.2025.103147_b115","unstructured":"Wikipedia. https:\/\/www.wikipedia.org\/."},{"key":"10.1016\/j.artmed.2025.103147_b116","series-title":"Proceedings of the tenth international conference on language resources and evaluation","first-page":"923","article-title":"OpenSubtitles2016: Extracting large parallel corpora from movie and TV subtitles","author":"Lison","year":"2016"},{"key":"10.1016\/j.artmed.2025.103147_b117","series-title":"Proceedings of the eighth international conference on language resources and evaluation","first-page":"2214","article-title":"Parallel data, tools and interfaces in OPUS","author":"Tiedemann","year":"2012"},{"key":"10.1016\/j.artmed.2025.103147_b118","series-title":"Proceedings of the tenth international conference on language resources and evaluation","first-page":"3530","article-title":"The United Nations parallel corpus v1.0","author":"Ziemski","year":"2016"},{"key":"10.1016\/j.artmed.2025.103147_b119","unstructured":"Koehn P. Europarl: A parallel corpus for statistical machine translation. In: Proceedings of machine translation summit x: papers. Phuket, Thailand; 2005, p. 79\u201386, URL https:\/\/aclanthology.org\/2005.mtsummit-papers.11."},{"key":"10.1016\/j.artmed.2025.103147_b120","series-title":"Proceedings of the 58th annual meeting of the association for computational linguistics","first-page":"4555","article-title":"ParaCrawl: Web-scale acquisition of parallel corpora","author":"Ba\u00f1\u00f3n","year":"2020"},{"key":"10.1016\/j.artmed.2025.103147_b121","series-title":"Proceedings of the ninth international conference on language resources and evaluation","first-page":"1850","article-title":"Billions of parallel words for free: Building and using the EU bookshop corpus","author":"Skadi\u0146\u0161","year":"2014"},{"key":"10.1016\/j.artmed.2025.103147_b122","series-title":"Proceedings of the 2020 conference on empirical methods in natural language processing","first-page":"5960","article-title":"CCAligned: A massive collection of cross-lingual web-document pairs","author":"El-Kishky","year":"2020"},{"key":"10.1016\/j.artmed.2025.103147_b123","series-title":"Proceedings of the eighth international conference on language resources and evaluation","first-page":"454","article-title":"DGT-TM: A freely available translation memory in 22 languages","author":"Steinberger","year":"2012"},{"key":"10.1016\/j.artmed.2025.103147_b124","series-title":"Proceedings of the 16th conference of the European chapter of the association for computational linguistics: main volume","first-page":"1351","article-title":"WikiMatrix: Mining 135M parallel sentences in 1620 language pairs from Wikipedia","author":"Schwenk","year":"2021"},{"key":"10.1016\/j.artmed.2025.103147_b125","series-title":"Proceedings of the seventh international conference on language resources and evaluation","article-title":"MultiUN: A multilingual corpus from united nation documents","author":"Eisele","year":"2010"},{"key":"10.1016\/j.artmed.2025.103147_b126","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1016\/j.protcy.2014.11.024","article-title":"Building subject-aligned comparable corpora and mining it for truly parallel sentence pairs","volume":"18","author":"Wo\u0142k","year":"2014","journal-title":"Procedia Technol"},{"key":"10.1016\/j.artmed.2025.103147_b127","series-title":"ACL2017","first-page":"263","article-title":"Tilde MODEL - multilingual open data for EU languages","author":"Rozis","year":"2017"},{"key":"10.1016\/j.artmed.2025.103147_b128","series-title":"Proceedings of the ninth workshop on statistical machine translation","year":"2014"},{"key":"10.1016\/j.artmed.2025.103147_b129","series-title":"Proceedings of the fourth conference on machine translation (volume 2: shared task papers, day 1)","first-page":"1","author":"Barrault","year":"2019"},{"key":"10.1016\/j.artmed.2025.103147_b130","series-title":"Proceedings of the fifth conference on machine translation","first-page":"1","article-title":"Findings of the 2020 conference on machine translation (WMT20)","author":"Barrault","year":"2020"},{"key":"10.1016\/j.artmed.2025.103147_b131","series-title":"NODALIDA, 131 of link\u00f6ping electronic conference proceedings","first-page":"263","article-title":"Tilde MODEL - multilingual open data for EU languages","author":"Rozis","year":"2017"},{"key":"10.1016\/j.artmed.2025.103147_b132","series-title":"Proceedings of the 2020 conference on empirical methods in natural language processing","first-page":"4512","article-title":"Making monolingual sentence embeddings multilingual using knowledge distillation","author":"Reimers","year":"2020"},{"key":"10.1016\/j.artmed.2025.103147_b133","series-title":"Proceedings of the 16th annual conference of the European association for machine translation","first-page":"261","article-title":"WIT3: Web inventory of transcribed and translated talks","author":"Cettolo","year":"2012"},{"key":"10.1016\/j.artmed.2025.103147_b134","series-title":"Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing (volume 1: long papers)","first-page":"6490","article-title":"CCMatrix: Mining billions of high-quality parallel sentences on the web","author":"Schwenk","year":"2021"},{"key":"10.1016\/j.artmed.2025.103147_b135","unstructured":"Pancur A, Erjavec T. The siParl corpus of Slovene parliamentary proceedings. In: Proceedings of the second parlaCLARIN workshop. Marseille, France: European Language Resources Association; p. 28\u201334, URL https:\/\/aclanthology.org\/2020.parlaclarin-1.6."},{"key":"10.1016\/j.artmed.2025.103147_b136","series-title":"No language left behind: Scaling human-centered machine translation","author":"Costa-juss\u00e0","year":"2022"}],"container-title":["Artificial Intelligence in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S093336572500082X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S093336572500082X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T06:19:28Z","timestamp":1748413168000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S093336572500082X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":136,"alternative-id":["S093336572500082X"],"URL":"https:\/\/doi.org\/10.1016\/j.artmed.2025.103147","relation":{},"ISSN":["0933-3657"],"issn-type":[{"value":"0933-3657","type":"print"}],"subject":[],"published":{"date-parts":[[2025,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Speech translation for multilingual medical education leveraged by large language models","name":"articletitle","label":"Article Title"},{"value":"Artificial Intelligence in Medicine","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.artmed.2025.103147","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"103147"}}