{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:41:59Z","timestamp":1775202119099,"version":"3.50.1"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031984617","type":"print"},{"value":"9783031984624","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-98462-4_29","type":"book-chapter","created":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T17:07:58Z","timestamp":1753031278000},"page":"228-235","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Multimodal Classroom Diarization with\u00a0GPT Re-scoring: Teacher or\u00a0Student?"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5348-3020","authenticated-orcid":false,"given":"Matthew","family":"Perez","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5774-5873","authenticated-orcid":false,"given":"Berk","family":"Coker","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9391-1806","authenticated-orcid":false,"given":"Kemal Berk","family":"Kocabagli","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2330-5600","authenticated-orcid":false,"given":"Jessica","family":"Vitale","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3289-4742","authenticated-orcid":false,"given":"Alyssa","family":"Van Camp","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,21]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Attia, A.A., Liu, J., Ai, W., Demszky, D., Espy-Wilson, C.: Kid-whisper: towards bridging the performance gap in automatic speech recognition for children vs. adults. In: Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society, vol.\u00a07, pp. 74\u201380 (2024)","DOI":"10.1609\/aies.v7i1.31618"},{"key":"29_CR2","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Nagrani, A., Zisserman, A.: VoxCeleb2: deep speaker recognition. In: INTERSPEECH (2018)","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Demszky, D., Wang, R., Geraghty, S., Yu, C.: Does feedback on talk time increase student engagement? Evidence from a randomized controlled trial on a math tutoring platform. In: Proceedings of the 14th Learning Analytics and Knowledge Conference, pp. 632\u2013644 (2024)","DOI":"10.1145\/3636555.3636924"},{"key":"29_CR4","doi-asserted-by":"publisher","unstructured":"Desplanques, B., Thienpondt, J., Demuynck, K.: ECAPA-TDNN: emphasized channel attention, propagation and aggregation in TDNN based speaker verification. In: Interspeech 2020, pp. 3830\u20133834 (2020). https:\/\/doi.org\/10.21437\/Interspeech.2020-2650","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"29_CR5","doi-asserted-by":"publisher","unstructured":"Flemotomos, N., Georgiou, P., Narayanan, S.: Linguistically aided speaker diarization using speaker role information. In: The Speaker and Language Recognition Workshop (Odyssey 2020), pp. 117\u2013124 (2020). https:\/\/doi.org\/10.21437\/Odyssey.2020-17","DOI":"10.21437\/Odyssey.2020-17"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Huang, Y., Wang, W., Zhao, G., Liao, H., Xia, W., Wang, Q.: On the success and limitations of auxiliary network based word-level end-to-end neural speaker diarization. In: Proceedings Interspeech 2024, pp. 32\u201336 (2024)","DOI":"10.21437\/Interspeech.2024-561"},{"issue":"6","key":"29_CR7","doi-asserted-by":"publisher","first-page":"1059","DOI":"10.1109\/JSTSP.2010.2081790","volume":"4","author":"P Kenny","year":"2010","unstructured":"Kenny, P., Reynolds, D., Castaldo, F.: Diarization of telephone conversations using factor analysis. IEEE J. Sel. Top. Sig. Process. 4(6), 1059\u20131070 (2010)","journal-title":"IEEE J. Sel. Top. Sig. Process."},{"issue":"7","key":"29_CR8","doi-asserted-by":"publisher","first-page":"2638","DOI":"10.3390\/s22072638","volume":"22","author":"A Khan","year":"2022","unstructured":"Khan, A., et al.: Toward realigning automatic speaker verification in the era of covid-19. Sensors 22(7), 2638 (2022)","journal-title":"Sensors"},{"issue":"4","key":"29_CR9","doi-asserted-by":"publisher","first-page":"933","DOI":"10.1007\/s10772-022-09990-9","volume":"25","author":"AK Kumar","year":"2022","unstructured":"Kumar, A.K., Waldekar, S., Sahidullah, M., Saha, G.: Robust acoustic domain identification with its application to speaker diarization. Int. J. Speech Technol. 25(4), 933\u2013945 (2022)","journal-title":"Int. J. Speech Technol."},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Li, J., Hasegawa-Johnson, M., McElwain, N.L.: Towards robust family-infant audio analysis based on unsupervised pretraining of Wav2vec 2.0 on large-scale unlabeled family audio. In: Proceedings Interspeech 2023, pp. 1035\u20131039 (2023)","DOI":"10.21437\/Interspeech.2023-460"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Nagrani, A., Chung, J.S., Zisserman, A.: VoxCeleb: a large-scale speaker identification dataset. In: INTERSPEECH (2017)","DOI":"10.21437\/Interspeech.2017-950"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Nagrani, A., Chung, J.S., Xie, W., Zisserman, A.: VoxCeleb: large-scale speaker verification in the wild. Comput. Sci. Lang. (2019)","DOI":"10.1016\/j.csl.2019.101027"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Sell, G., Garcia-Romero, D.: Speaker diarization with PLDA I-vector scoring and unsupervised calibration. In: 2014 IEEE Spoken Language Technology Workshop (SLT), pp. 413\u2013417. IEEE (2014)","DOI":"10.1109\/SLT.2014.7078610"},{"key":"29_CR14","doi-asserted-by":"publisher","unstructured":"Shafey, L.E., Soltau, H., Shafran, I.: Joint speech recognition and speaker diarization via sequence transduction. In: Interspeech 2019, pp. 396\u2013400 (2019). https:\/\/doi.org\/10.21437\/Interspeech.2019-1943","DOI":"10.21437\/Interspeech.2019-1943"},{"key":"29_CR15","unstructured":"Wang, J., Dudy, S., He, X., Wang, Z., Southwell, R., Whitehill, J.: Speaker diarization in the classroom: how much does each student speak in group discussions? In: Proceedings of the 17th International Conference on Educational Data Mining, pp. 360\u2013367 (2024)"},{"issue":"1","key":"29_CR16","first-page":"98","volume":"17","author":"J Wang","year":"2025","unstructured":"Wang, J., et al.: Optimizing speaker diarization for the classroom: applications in timing student speech and distinguishing teachers from children. J. Educ. Data Mining 17(1), 98\u2013125 (2025)","journal-title":"J. Educ. Data Mining"},{"key":"29_CR17","unstructured":"Wang, Q., Huang, Y., Lu, H., Zhao, G., Moreno, I.L.: Highly efficient real-time streaming and fully on-device speaker diarization with multi-stage clustering. arXiv preprint arXiv:2210.13690 (2022)"},{"key":"29_CR18","doi-asserted-by":"publisher","unstructured":"Wang, Q., Huang, Y., Zhao, G., Clark, E., Xia, W., Liao, H.: DiarizationLM: speaker diarization post-processing with large language models. In: Interspeech 2024, pp. 3754\u20133758 (2024). https:\/\/doi.org\/10.21437\/Interspeech.2024-209","DOI":"10.21437\/Interspeech.2024-209"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Yang, Y., Achananuparp, P., Huang, H.Y., Jiang, J., Lim, E.P.: Speaker verification in agent-generated conversations. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 5655\u20135676 (2024)","DOI":"10.18653\/v1\/2024.acl-long.307"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence in Education"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-98462-4_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T05:29:40Z","timestamp":1775194180000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-98462-4_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031984617","9783031984624"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-98462-4_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"21 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AIED","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Intelligence in Education","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Palermo","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":"22 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aied2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aied2025.itd.cnr.it\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}