{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T01:43:13Z","timestamp":1772674993139,"version":"3.50.1"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032073426","type":"print"},{"value":"9783032073433","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\/978-3-032-07343-3_8","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:10:34Z","timestamp":1767312634000},"page":"96-108","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["CymruFluency - A Fusion Technique and a 4D Welsh Dataset for Welsh Fluency Analysis"],"prefix":"10.1007","author":[{"given":"Arvinder Pal Singh","family":"Bali","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gary K. L.","family":"Tam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Avishek","family":"Siris","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gareth","family":"Andrews","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yukun","family":"Lai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bernie","family":"Tiddeman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gwenno","family":"Ffrancon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"8_CR1","unstructured":"3dMD: 3D Face Imaging Systems. https:\/\/3dmd.com\/"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Active shape models-their training and application. Comput. Vis. Image Underst. 61(1), 38\u201359 (1995)","DOI":"10.1006\/cviu.1995.1004"},{"key":"8_CR3","unstructured":"Agrija, contributors: Avalinguo audio set. https:\/\/github.com\/agrija9\/Avalinguo-Audio-Set. Accessed 12 Feb 2025"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Anwar, M., Shi, B., Goswami, V., Hsu, W.N., Pino, J., Wang, C.: Muavic: a multilingual audio-visual corpus for robust speech recognition and robust speech-to-text translation. In: Proceedings of INTERSPEECH (2023)","DOI":"10.21437\/Interspeech.2023-2279"},{"key":"8_CR5","unstructured":"Ardila, R., et al.: Common voice: a massively-multilingual speech corpus. In: Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pp. 4211\u20134215 (2020)"},{"key":"8_CR6","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.jfludis.2018.03.002","volume":"56","author":"N Bernstein Ratner","year":"2018","unstructured":"Bernstein Ratner, N., MacWhinney, B.: Fluency bank: a new resource for fluency research and practice. J. Fluency Disord. 56, 69\u201380 (2018)","journal-title":"J. Fluency Disord."},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Brena, R., Zuvirie, E., Preciado\u00a0Grijalva, A., Valdiviezo, A., Gonzalez-Mendoza, M., Zozaya-Gorostiza, C.: Automated evaluation of foreign language speaking performance with machine learning. Int. J. Interact. Des. Manufact. (IJIDeM) 15, 1\u201315 (2021)","DOI":"10.1007\/s12008-021-00759-z"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4724\u20134733 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder\u2013decoder for statistical machine translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1724\u20131734 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"issue":"3","key":"8_CR10","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1111\/1460-6984.12363","volume":"53","author":"V Chondrogianni","year":"2018","unstructured":"Chondrogianni, V., John, N.: Tense and plural formation in welsh\u2013english bilingual children with and without language impairment. Int. J. Lang. Commun. Disord. 53(3), 495\u2013514 (2018)","journal-title":"Int. J. Lang. Commun. Disord."},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Zisserman, A.: Lip reading in the wild. In: Proceedings of ACCV, pp. 87\u2013103 (2017)","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Das, A., Mock, J., Huang, Y., Golob, E., Najafirad, P.: Interpretable self-supervised facial micro-expression learning to predict cognitive state and neurological disorders. Proc. AAAI 35(1), 818\u2013826 (2021)","DOI":"10.1609\/aaai.v35i1.16164"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Devi, T.M., Keerthana, S., Santhi, P., Pravallika, P., Rajeshwari, S.: Silent speech recognition: automatic lip reading model using 3D CNN and GRU. In: Proceedings of the 5th International Conference on Data Science, Machine Learning and Applications; Volume 1, pp. 827\u2013832 (2025)","DOI":"10.1007\/978-981-97-8031-0_88"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Gothi, R., Kumar, R., Pereira, M., Nayak, N., Rao, P.: A dataset and two-pass system for reading miscue detection. In: Proceedings of INTERSPEECH, pp. 123\u2013130 (2024)","DOI":"10.21437\/Interspeech.2024-1639"},{"issue":"8","key":"8_CR15","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"8_CR16","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s13735-024-00341-9","volume":"13","author":"J Huang","year":"2024","unstructured":"Huang, J., Kang, H.: 3D skeleton-based human motion prediction using spatial-temporal graph convolutional network. Int. J. Multimedia Inf. Retrieval 13, 33 (2024)","journal-title":"Int. J. Multimedia Inf. Retrieval"},{"key":"8_CR17","unstructured":"Kourkounakis, T.: UCLASS Stutter Annotations (2021). https:\/\/doi.org\/10.5683\/SP3\/1FIUHM"},{"key":"8_CR18","doi-asserted-by":"publisher","first-page":"2986","DOI":"10.1109\/TASLP.2021.3110146","volume":"29","author":"T Kourkounakis","year":"2021","unstructured":"Kourkounakis, T., Hajavi, A., Etemad, A.: Fluentnet: end-to-end detection of stuttered speech disfluencies with deep learning. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 2986\u20132999 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Lea, C., Mitra, V., Joshi, A., Kajarekar, S., Bigham, J.P.: Sep-28k: a dataset for stuttering event detection from podcasts with people who stutter. In: Proceedings of ICASSP, pp. 6798\u20136802 (2021)","DOI":"10.1109\/ICASSP39728.2021.9413520"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Liu, J., Wumaier, A., Fan, C., Guo, S.: Automatic fluency assessment method for spontaneous speech without reference text. Electronics 12(8) (2023)","DOI":"10.3390\/electronics12081775"},{"key":"8_CR21","doi-asserted-by":"publisher","first-page":"20429","DOI":"10.1007\/s11042-020-08917-3","volume":"79","author":"PE Martin","year":"2020","unstructured":"Martin, P.E., Benois-Pineau, J., P\u00e9teri, R., Morlier, J.: Fine grained sport action recognition with twin spatio-temporal convolutional neural networks. Multimedia Tools Appl. 79, 20429\u201320447 (2020)","journal-title":"Multimedia Tools Appl."},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Mazzeo, P.L., Spagnolo, P., Fasano, M., Distante, C.: Human action recognition with transformers. In: Sclaroff, S., Distante, C., Leo, M., Farinella, G.M., Tombari, F. (eds.) Image Analysis and Processing \u2013 ICIAP 2022 (2022)","DOI":"10.1007\/978-3-031-06433-3_20"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Alabort-i Medina, J., Antonakos, E., Booth, J., Snape, P., Zafeiriou, S.: Menpo: a comprehensive platform for parametric image alignment and visual deformable models. In: ACM International Conference on Multimedia, pp. 679\u2013682 (2014)","DOI":"10.1145\/2647868.2654890"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Mohapatra, P., Likhite, S., Biswas, S., Islam, B., Zhu, Q.: Missingness-resilient video-enhanced multimodal disfluency detection. In: Proceedings of INTERSPEECH, pp. 5093\u20135097 (2024)","DOI":"10.21437\/Interspeech.2024-1458"},{"issue":"1","key":"8_CR25","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1111\/1460-6984.12674","volume":"57","author":"L Mulgrew","year":"2022","unstructured":"Mulgrew, L., Duffy, O., Kennedy, L.: Assessment of minority language skills in english\u2013irish-speaking bilingual children: a survey of SLT perspectives and current practices. Int. J. Lang. Commun. Disord. 57(1), 63\u201377 (2022)","journal-title":"Int. J. Lang. Commun. Disord."},{"issue":"4","key":"8_CR26","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1109\/TMM.2009.2017629","volume":"11","author":"P Nair","year":"2009","unstructured":"Nair, P., Cavallaro, A.: 3-D face detection, landmark localization, and registration using a point distribution model. Trans. Multimedia 11(4), 611\u2013623 (2009)","journal-title":"Trans. Multimedia"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Nie, L., Kadiri, S.R., Agrawal, R.: Mmsd-net: towards multi-modal stuttering detection. In: Proceedings of INTERSPEECH, pp. 5113\u20135117 (2024)","DOI":"10.21437\/Interspeech.2024-1497"},{"key":"8_CR28","doi-asserted-by":"crossref","unstructured":"Panda, A., Acharya, R., Kopparapu, S.K.: Oral fluency classification for speech assessment. In: The 31st European Signal Processing Conference (EUSIPCO) (2023)","DOI":"10.23919\/EUSIPCO58844.2023.10289791"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Sagonas, C., Tzimiropoulos, G., Zafeiriou, S., Pantic, M.: 300 faces in-the-wild challenge: the first facial landmark localization challenge. In: IEEE ICCV-Workshop, 300 Faces in-the-Wild Challenge (300-W) (2013)","DOI":"10.1109\/ICCVW.2013.59"},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Sayed, H.M., ElDeeb, H.E., Taie, S.A.: Multimodal data fusion architectures in audiovisual speech recognition. In: Information Systems and Technologies, pp. 655\u2013667 (2024)","DOI":"10.1007\/978-3-031-45645-9_63"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Srivastava, S., Singh, S., Pooja, Prakash, S.: Continuous sign language recognition system using deep learning with mediapipe holistic. Wirel. Pers. Commun. 137, 1455\u20131468 (2024)","DOI":"10.1007\/s11277-024-11356-0"},{"key":"8_CR32","doi-asserted-by":"crossref","unstructured":"Sung-Bin, K., et al.: Multitalk: enhancing 3D talking head generation across languages with multilingual video dataset. In: Proceedings of INTERSPEECH, pp. 1380\u20131384 (2024)","DOI":"10.21437\/Interspeech.2024-1794"},{"issue":"4","key":"8_CR33","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1109\/34.88573","volume":"13","author":"S Umeyama","year":"1991","unstructured":"Umeyama, S.: Least-squares estimation of transformation parameters between two point patterns. IEEE TPAMI 13(4), 376\u2013380 (1991)","journal-title":"IEEE TPAMI"},{"key":"8_CR34","unstructured":"Waswani, A., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"8_CR35","unstructured":"Welsh Government: Welsh language data from the annual population survey (Oct 2023 - Sep 2024). Technical report, Welsh Government (2024)"},{"key":"8_CR36","unstructured":"Welsh Government: Welsh language technology action plan: Final report 2018-2024. Technical report, Welsh Government (2024)"},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: speechocean762: An open-source non-native english speech corpus for pronunciation assessment. In: Proceedings of INTERSPEECH (2021)","DOI":"10.21437\/Interspeech.2021-1259"},{"key":"8_CR38","doi-asserted-by":"crossref","unstructured":"Zhao, F., Zhang, C., Geng, B.: Deep multimodal data fusion. ACM Comput. Surv. 56(9) (2024)","DOI":"10.1145\/3649447"}],"container-title":["Lecture Notes in Computer Science","Advanced Concepts for Intelligent Vision Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-07343-3_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:10:37Z","timestamp":1767312637000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-07343-3_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032073426","9783032073433"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-07343-3_8","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":"ACIVS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advanced Concepts for Intelligent Vision Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tokyo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"28 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"acivs2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.acivs2025.com","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}