{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T23:35:52Z","timestamp":1776900952684,"version":"3.51.2"},"publisher-location":"Cham","reference-count":11,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032167071","type":"print"},{"value":"9783032167088","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-3-032-16708-8_2","type":"book-chapter","created":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T22:41:43Z","timestamp":1776897703000},"page":"21-34","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Using Multi-modal Generative Models for\u00a0Creating Speech Therapy Material"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8043-8752","authenticated-orcid":false,"given":"Mihir","family":"Mulye","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2788-3854","authenticated-orcid":false,"given":"Stefan","family":"Conrad","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1056-9228","authenticated-orcid":false,"given":"Stefan","family":"Knecht","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,4,1]]},"reference":[{"key":"2_CR1","unstructured":"Achiam, J., et\u00a0al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"issue":"1S","key":"2_CR2","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1044\/2017_AJSLP-16-0190","volume":"27","author":"J Brown","year":"2018","unstructured":"Brown, J., Thiessen, A.: Using images with individuals with aphasia: Current research and clinical trends. Am. J. Speech Lang. Pathol. 27(1S), 504\u2013515 (2018)","journal-title":"Am. J. Speech Lang. Pathol."},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: Clipscore: A reference-free evaluation metric for image captioning. arXiv preprint arXiv:2104.08718 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Hu, Y., et al.: Tifa: accurate and interpretable text-to-image faithfulness evaluation with question answering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20406\u201320417 (2023)","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"2_CR5","first-page":"34892","volume":"36","author":"H Liu","year":"2023","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural. Inf. Process. Syst. 36, 34892\u201334916 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR6","unstructured":"Mulye, M., Conrad, S., Knecht, S.: Proof of clinical feasibility of natural language learning with machines. In: Proceedings of the 35th GI-Workshop Grundlagen von Datenbanken (GvDB 2024). vol.\u00a03710. CEUR-WS.org (2024)"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Mulye, M., Conrad, S., Knecht, S.: Exploring applicability of text-to-image models for generating aphasia rehabilitation material. In: International Conference on AI in Healthcare, pp. 324\u2013338. Springer (2025)","DOI":"10.1007\/978-3-032-00652-3_23"},{"issue":"1","key":"2_CR8","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1044\/2023_AJSLP-23-00142","volume":"33","author":"JE Pierce","year":"2024","unstructured":"Pierce, J.E.: Ai-generated images for speech pathology\u2013an exploratory application to aphasia assessment and intervention materials. Am. J. Speech Lang. Pathol. 33(1), 443\u2013451 (2024)","journal-title":"Am. J. Speech Lang. Pathol."},{"key":"2_CR9","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"2_CR10","unstructured":"Team, G., et\u00a0al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"2_CR11","unstructured":"Team, Q.: Qwen2.5: A party of foundation models (September 2024). https:\/\/qwenlm.github.io\/blog\/qwen2.5\/"}],"container-title":["Communications in Computer and Information Science","Artificial Intelligence for Healthcare, and Hybrid Models for Coupling Deductive and Inductive Reasoning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-16708-8_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T22:41:44Z","timestamp":1776897704000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-16708-8_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032167071","9783032167088"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-16708-8_2","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 April 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"HC_AIxIA_HYDRA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Joint Workshop on Artificial Intelligence for Healthcare, and Hybrid Models for Coupling Deductive and Inductive Reasoning","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bologna","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"25 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"hc_aixia_hydra2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/sites.google.com\/unical.it\/hcaixia-hydra-2025\/home","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}