{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:07:58Z","timestamp":1767323278597,"version":"3.48.0"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032139603","type":"print"},{"value":"9783032139610","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\/978-3-032-13961-0_6","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:03:45Z","timestamp":1767323025000},"page":"51-60","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Radar-Driven Speech Therapy: Multimodal Training with\u00a0Ultrasound, Audio, and\u00a0Radar for\u00a0Unimodal Phonetic Segment Classification"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4237-8442","authenticated-orcid":false,"given":"Ilhan","family":"Aytutuldu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6952-6735","authenticated-orcid":false,"given":"Yakup","family":"Genc","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8501-4812","authenticated-orcid":false,"given":"Yusuf Sinan","family":"Akgul","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"6_CR1","unstructured":"Annand, C.T., et\u00a0al.: Using ultrasound imaging to create augmented visual biofeedback for articulatory practice. In: INTERSPEECH, pp. 974\u2013975 (2019)"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Aytutuldu, I., Bilici, Z., Genc, Y., Akgul, Y.S.: Indoor human counting based on range-doppler spectrum in the presence of material penetration and occlusion. In: 2024 6th International Conference on Communications, Signal Processing, and their Applications (ICCSPA), pp.\u00a01\u20135. IEEE (2024)","DOI":"10.1109\/ICCSPA61559.2024.10794279"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Aytutuldu, I., Genc, Y., Akgul, Y.S.: Audio-only phonetic segment classification using embeddings learned from audio and ultrasound tongue imaging data. IEEE\/ACM Trans. Audio Speech Lang. Process. (2024)","DOI":"10.1109\/TASLP.2024.3473316"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Beeson, R., Richmond, K.: Silent speech recognition with articulator positions estimated from tongue ultrasound and lip video. In: Interspeech 2023, pp. 1149\u20131153. ISCA (2023)","DOI":"10.21437\/Interspeech.2023-1966"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Bilici, Z., Aytutuldu, I., Genc, Y., Akgul, Y.S.: mmWave frequency modulated continuous wave radar-based human action recognition. In: 2024 32nd Signal Processing and Communications Applications Conference (SIU), pp.\u00a01\u20134. IEEE (2024)","DOI":"10.1109\/SIU61531.2024.10600787"},{"issue":"3","key":"6_CR6","doi-asserted-by":"publisher","first-page":"543","DOI":"10.3390\/s17030543","volume":"17","author":"F Chen","year":"2017","unstructured":"Chen, F., Li, S., Zhang, Y., Wang, J.: Detection of the vibration signal from human vocal folds using a 94-ghz millimeter-wave radar. Sensors 17(3), 543 (2017)","journal-title":"Sensors"},{"key":"6_CR7","doi-asserted-by":"publisher","unstructured":"Chen, T., et al.: Ultrasound image-to-video synthesis via latent dynamic diffusion models. In: proceedings of Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024. LNCS, vol. 15004. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72083-3_71","DOI":"10.1007\/978-3-031-72083-3_71"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Cleland, J.: Ultrasound tongue imaging in research and practice with people with cleft palate$$\\pm $$cleft lip. Cleft Palate Craniofacial J. 10556656231202448 (2023)","DOI":"10.1177\/10556656231202448"},{"key":"6_CR9","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.specom.2021.05.008","volume":"132","author":"A Eshky","year":"2021","unstructured":"Eshky, A., Cleland, J., Ribeiro, M.S., Sugden, E., Richmond, K., Renals, S.: Automatic audiovisual synchronisation for ultrasound tongue imaging. Speech Commun. 132, 83\u201395 (2021)","journal-title":"Speech Commun."},{"key":"6_CR10","unstructured":"Instruments, A.: Articulate assistant advanced user guide: Version 2.16. Articulate Instruments Ltd (2012)"},{"key":"6_CR11","doi-asserted-by":"publisher","DOI":"10.1201\/9781420015836","volume-title":"Speech Enhancement: Theory and Practice","author":"PC Loizou","year":"2007","unstructured":"Loizou, P.C.: Speech Enhancement: Theory and Practice. CRC Press, Boca Raton (2007)"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Ozturk, M.Z., Wu, C., Wang, B., Liu, K.R.: Sound recovery from radio signals. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8022\u20138026. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9413508"},{"issue":"5","key":"6_CR13","doi-asserted-by":"publisher","first-page":"4431","DOI":"10.1109\/JIOT.2022.3217968","volume":"10","author":"MZ Ozturk","year":"2022","unstructured":"Ozturk, M.Z., Wu, C., Wang, B., Liu, K.R.: Radiomic: sound sensing via radio signals. IEEE Internet Things J. 10(5), 4431\u20134448 (2022)","journal-title":"IEEE Internet Things J."},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.S., Eshky, A., Richmond, K., Renals, S.: Speaker-independent classification of phonetic segments from raw ultrasound in child speech. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1328\u20131332. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683564"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Tatulli, E., Hueber, T.: Feature extraction using multimodal convolutional neural networks for visual speech recognition. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2971\u20132975. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952701"},{"key":"6_CR16","unstructured":"Wang, D., Brown, G.J.: Computational Auditory Scene Analysis: Principles, Algorithms, and Applications. Wiley-IEEE press, Hoboken (2006)"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Wu, H., et al.: Towards multi-modality fusion and prototype-based feature refinement for clinically significant prostate cancer classification in transrectal ultrasound. In: proceedings of Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024. LNCS, vol. 15005. Springer, Heidelberg (2024)","DOI":"10.1007\/978-3-031-72086-4_68"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Xu, K., Roussel, P., Csap\u00f3, T.G., Denby, B.: Convolutional neural network-based automatic classification of midsagittal tongue gestural targets using b-mode ultrasound images. J. Acoust. Soc. Am. 141(6), EL531\u2013EL537 (2017)","DOI":"10.1121\/1.4984122"},{"issue":"1","key":"6_CR19","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1109\/TASLP.2014.2364452","volume":"23","author":"Y Xu","year":"2014","unstructured":"Xu, Y., Du, J., Dai, L.R., Lee, C.H.: A regression approach to speech enhancement based on deep neural networks. IEEE\/ACM Trans. Audio Speech Lang. Process. 23(1), 7\u201319 (2014)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"6_CR20","doi-asserted-by":"publisher","first-page":"1430","DOI":"10.1109\/TASLP.2024.3361376","volume":"32","author":"RC Zheng","year":"2024","unstructured":"Zheng, R.C., Ai, Y., Ling, Z.H.: Incorporating ultrasound tongue images for audio-visual speech enhancement. IEEE\/ACM Trans. Audio Speech Lang. Process. 32, 1430\u20131444 (2024). https:\/\/doi.org\/10.1109\/TASLP.2024.3361376","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Zheng, R.C., Ai, Y., Ling, Z.H.: Incorporating ultrasound tongue images for audio-visual speech enhancement. IEEE\/ACM Trans. Audio Speech Lang. Process. (2024)","DOI":"10.1109\/TASLP.2024.3361376"}],"container-title":["Lecture Notes in Computer Science","Efficient Medical Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-13961-0_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:03:47Z","timestamp":1767323027000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-13961-0_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032139603","9783032139610"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-13961-0_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare\u00a0that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"EMA4MICCAI 2025","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Efficient Medical Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","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":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 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":"ema4miccai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/sites.google.com\/view\/ema4miccai2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}