{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T07:43:35Z","timestamp":1760255015588,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032079558","type":"print"},{"value":"9783032079565","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-07956-5_4","type":"book-chapter","created":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T07:19:10Z","timestamp":1760253550000},"page":"52-66","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Prompting the\u00a0Mind: EEG-to-Text Translation with\u00a0Multimodal LLMs and\u00a0Semantic Control"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3094-6916","authenticated-orcid":false,"given":"Mohammed Salah","family":"Al-Radhi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1594-2614","authenticated-orcid":false,"given":"Sadi Mahmud","family":"Shurid","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2311-4858","authenticated-orcid":false,"given":"G\u00e9za","family":"N\u00e9meth","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,13]]},"reference":[{"key":"4_CR1","doi-asserted-by":"publisher","first-page":"429","DOI":"10.3389\/fnins.2016.00429","volume":"10","author":"C Herff","year":"2016","unstructured":"Herff, C., Schultz, T.: Automatic speech recognition from neural signals: a focused review. Front. Neurosci. 10, 429 (2016). https:\/\/doi.org\/10.3389\/fnins.2016.00429","journal-title":"Front. Neurosci."},{"key":"4_CR2","doi-asserted-by":"publisher","unstructured":"D\u00e9fossez, A., Caucheteux, C., Rapin, J., Kabeli, O., King, J.R.: Decoding speech perception from non-invasive brain recordings. Nat. Mach. Intell. 5, 1097\u20131107 (2023). https:\/\/doi.org\/10.1038\/s42256-023-00714-5","DOI":"10.1038\/s42256-023-00714-5"},{"key":"4_CR3","doi-asserted-by":"publisher","unstructured":"Pfeffer, M.A., Ling, S.S.H., Wong, J.K.W.: Exploring the frontier: transformer-based models in EEG signal analysis for brain-computer interfaces. Comput. Biol. Med. 178, 108705 (2024). https:\/\/doi.org\/10.1016\/j.compbiomed.2024.108705","DOI":"10.1016\/j.compbiomed.2024.108705"},{"key":"4_CR4","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1038\/s41593-020-0608-8","volume":"23","author":"JG Makin","year":"2020","unstructured":"Makin, J.G., Moses, D.A., Chang, E.F.: Machine translation of cortical activity to text with an encoder-decoder framework. Nat. Neurosci. 23, 575\u2013582 (2020). https:\/\/doi.org\/10.1038\/s41593-020-0608-8","journal-title":"Nat. Neurosci."},{"key":"4_CR5","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1038\/s41586-021-03506-2","volume":"593","author":"FR Willett","year":"2021","unstructured":"Willett, F.R., Moses, D.A., Shenoy, K.V., Chang, E.F.: High-performance brain-to-text communication via handwriting decoding. Nature 593, 249\u2013254 (2021). https:\/\/doi.org\/10.1038\/s41586-021-03506-2","journal-title":"Nature"},{"key":"4_CR6","doi-asserted-by":"publisher","unstructured":"Touvron, H., Lavril, T., Izacard, G., et al.: LLaMA: open and efficient foundation language models. Preprint at arXiv (2023https:\/\/doi.org\/10.48550\/arXiv.2302.13971","DOI":"10.48550\/arXiv.2302.13971"},{"key":"4_CR7","doi-asserted-by":"publisher","first-page":"26839","DOI":"10.1109\/ACCESS.2024.3365742","volume":"12","author":"MAK Raiaan","year":"2024","unstructured":"Raiaan, M.A.K., et al.: A review on large language models: architectures, applications, taxonomies. Open Issues and Challenges. IEEE Access 12, 26839\u201326874 (2024). https:\/\/doi.org\/10.1109\/ACCESS.2024.3365742","journal-title":"Open Issues and Challenges. IEEE Access"},{"key":"4_CR8","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s41586-019-1119-1","volume":"568","author":"GK Anumanchipalli","year":"2019","unstructured":"Anumanchipalli, G.K., Chartier, J., Chang, E.F.: Speech synthesis from neural decoding of spoken sentences. Nature 568, 493\u2013498 (2019). https:\/\/doi.org\/10.1038\/s41586-019-1119-1","journal-title":"Nature"},{"issue":"6","key":"4_CR9","doi-asserted-by":"publisher","first-page":"1044","DOI":"10.1109\/TBME.2004.826692","volume":"51","author":"B Blankertz","year":"2004","unstructured":"Blankertz, B., M\u00fcller, K.R., Curio, G., Vaughan, T.M., et al.: The BCI competition 2003: progress and perspectives in detection and discrimination of EEG single trials. IEEE Trans. Biomed. Eng. 51(6), 1044\u20131051 (2004). https:\/\/doi.org\/10.1109\/TBME.2004.826692","journal-title":"IEEE Trans. Biomed. Eng."},{"issue":"5","key":"4_CR10","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/aace8c","volume":"15","author":"VJ Lawhern","year":"2018","unstructured":"Lawhern, V.J., Solon, A.J., Waytowich, N.R., Gordon, S.M., Hung, C.P., Lance, B.J.: EEGNet: a compact convolutional neural network for EEG-based brain\u2013computer interfaces. J. Neural Eng. 15(5), 056013 (2018). https:\/\/doi.org\/10.1088\/1741-2552\/aace8c","journal-title":"J. Neural Eng."},{"key":"4_CR11","doi-asserted-by":"publisher","unstructured":"Mishra, A., Shukla, S., Torres, J., Gwizdka, J., Roychowdhury, S.: Thought2Text: text generation from EEG signal using large language models (LLMs). In: Findings of the Association for Computational Linguistics: NAACL 2025, Albuquerque, New Mexico, pp. 3747\u20133759 (2025). https:\/\/doi.org\/10.18653\/v1\/2025.findings-naacl.207","DOI":"10.18653\/v1\/2025.findings-naacl.207"},{"key":"4_CR12","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of the 38th International Conference on Machine Learning (ICML), Proceedings of Machine Learning Research, vol. 139, pp. 8748\u20138763 (2021). http:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"4_CR13","doi-asserted-by":"publisher","unstructured":"Bi, X., Chen, D., Chen, G., Chen, S., et al.: DeepSeek LLM: scaling open-source language models with Longtermism. Preprint at arXiv (2024https:\/\/doi.org\/10.48550\/arXiv.2401.02954","DOI":"10.48550\/arXiv.2401.02954"},{"issue":"11","key":"4_CR14","doi-asserted-by":"publisher","first-page":"3833","DOI":"10.1109\/TPAMI.2020.2995909","volume":"43","author":"S Palazzo","year":"2021","unstructured":"Palazzo, S., Spampinato, C., Kavasidis, I., Giordano, D., Schmidt, J., Shah, M.: Decoding brain representations by multimodal learning of neural activity and visual features. IEEE Trans. Pattern Anal. Mach. Intell. 43(11), 3833\u20133849 (2021). https:\/\/doi.org\/10.1109\/TPAMI.2020.2995909","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4_CR15","doi-asserted-by":"publisher","unstructured":"Jiang, A.Q., Sablayrolles, A., Mensch, A., Bamford, C., et al.: Mistral 7B. Preprint at arXiv (2023). https:\/\/doi.org\/10.48550\/arXiv.2310.06825","DOI":"10.48550\/arXiv.2310.06825"},{"key":"4_CR16","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: BERTScore: evaluating text generation with BERT. In: Proceedings of the 8th International Conference on Learning Representations (ICLR), Addis Ababa, Ethiopia (2020). https:\/\/openreview.net\/forum?id=SkeHuCVFDr"},{"key":"4_CR17","doi-asserted-by":"publisher","unstructured":"Kamble, A., Ghare, P.H., Kumar, V.: Classifying phonological categories and imagined words from EEG signal. Biomedical Signal Processing for Healthcare Applications, 1st ed., CRC Press, pp. 1\u201329 (2021). https:\/\/doi.org\/10.1201\/9781003147817","DOI":"10.1201\/9781003147817"},{"key":"4_CR18","doi-asserted-by":"publisher","unstructured":"Torres-Garc\u00eda, A.A., Reyes-Garc\u00eda, C.A., Villase\u00f1or-Pineda, L.: A survey on EEG-based imagined speech classification. Biosignal Processing and Classification Using Computational Learning and Intelligence, Academic Press, pp. 251\u2013270 (2022). https:\/\/doi.org\/10.1016\/B978-0-12-820125-1.00025-7","DOI":"10.1016\/B978-0-12-820125-1.00025-7"},{"key":"4_CR19","doi-asserted-by":"publisher","unstructured":"Sharon, R.A., Narayanan, S., Sur, M., Murthy, H.A.: An empirical study of speech processing in the brain by analyzing the temporal syllable structure in speech-input induced EEG. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK, pp. 4090\u20134094 (2019). https:\/\/doi.org\/10.1109\/ICASSP.2019.8683572","DOI":"10.1109\/ICASSP.2019.8683572"},{"key":"4_CR20","doi-asserted-by":"publisher","unstructured":"Sakthi, M., Desai, M., Hamilton, L., Tewfik, A.: Keyword-spotting and speech onset detection in EEG-based brain computer interfaces. In: Proceedings of the 10th International IEEE\/EMBS Conference on Neural Engineering (NER), Italy, pp. 519\u2013522 (2021). https:\/\/doi.org\/10.1109\/NER49283.2021.9441118","DOI":"10.1109\/NER49283.2021.9441118"},{"key":"4_CR21","doi-asserted-by":"publisher","first-page":"761","DOI":"10.1038\/s41593-020-0639-1","volume":"23","author":"P Gui","year":"2020","unstructured":"Gui, P., Jiang, Y., Zang, D., et al.: Assessing the depth of language processing in patients with disorders of consciousness. Nat. Neurosci. 23, 761\u2013770 (2020). https:\/\/doi.org\/10.1038\/s41593-020-0639-1","journal-title":"Nat. Neurosci."},{"issue":"9","key":"4_CR22","doi-asserted-by":"publisher","first-page":"10760","DOI":"10.1109\/TPAMI.2023.3263181","volume":"45","author":"C Du","year":"2023","unstructured":"Du, C., Fu, K., Li, J., He, H.: Decoding visual neural representations by multimodal learning of brain-visual-linguistic features. IEEE Trans. Pattern Anal. Mach. Intell. 45(9), 10760\u201310777 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2023.3263181","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4_CR23","doi-asserted-by":"publisher","unstructured":"Spampinato, C., Palazzo, S., Kavasidis, I., Giordano, D., Souly, N., Shah, M.: Deep learning human mind for automated visual classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, pp. 4503\u20134511 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.479","DOI":"10.1109\/CVPR.2017.479"},{"key":"4_CR24","doi-asserted-by":"publisher","unstructured":"Cai, J., Hadjinicolaou, A.E., Paulk, A.C., et al.: Natural language processing models reveal neural dynamics of human conversation. Nat. Commun. 16, 3376 (2025). https:\/\/doi.org\/10.1038\/s41467-025-58620-w","DOI":"10.1038\/s41467-025-58620-w"},{"key":"4_CR25","doi-asserted-by":"publisher","unstructured":"Ahmadian, P., Cagnoni, S., Ascari, L.: How capable is non-invasive EEG data of predicting the next movement? A mini review. Front. Hum. Neurosci. 7, 124 (2013). https:\/\/doi.org\/10.3389\/fnhum.2013.00124","DOI":"10.3389\/fnhum.2013.00124"},{"key":"4_CR26","doi-asserted-by":"publisher","unstructured":"Xing, J., et al.: A survey of efficient fine-tuning methods for vision-language models \u2014 prompt and adapter. Comput. Graph. 119, 103885 (2024). https:\/\/doi.org\/10.1016\/j.cag.2024.01.012","DOI":"10.1016\/j.cag.2024.01.012"},{"key":"4_CR27","doi-asserted-by":"publisher","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL), Philadelphia, PA, USA, pp. 311\u2013318 (2002). https:\/\/doi.org\/10.3115\/1073083.1073135","DOI":"10.3115\/1073083.1073135"},{"key":"4_CR28","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, Ann Arbor, Michigan, pp. 65\u201372 (2005). https:\/\/aclanthology.org\/W05-0909\/"},{"key":"4_CR29","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, Barcelona, Spain, pp. 74\u201381 (2004). https:\/\/aclanthology.org\/W04-1013\/"},{"key":"4_CR30","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: BERTScore: evaluating text generation with BERT. In: International Conference on Learning Representations (ICLR), pp. 1\u201343 (2020). http:\/\/www.openreview.net\/pdf?id=SkeHuCVFDr"},{"key":"4_CR31","unstructured":"Al-Radhi, M.S., N\u00e9meth, G., Gerazov, B.: MiSTR: multi-modal iEEG-to-speech synthesis with transformer-based prosody prediction and neural phase reconstruction. In: Proceedings of Interspeech 2025, Rotterdam, The Netherlands, pp. 1\u20135 (2025)"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-07956-5_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T07:19:34Z","timestamp":1760253574000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-07956-5_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,13]]},"ISBN":["9783032079558","9783032079565"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-07956-5_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,13]]},"assertion":[{"value":"13 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Szeged","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hungary","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/specom.inf.u-szeged.hu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}