{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,21]],"date-time":"2025-12-21T06:26:26Z","timestamp":1766298386447,"version":"3.37.3"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T00:00:00Z","timestamp":1740009600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T00:00:00Z","timestamp":1740009600000},"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":["SN COMPUT. SCI."],"DOI":"10.1007\/s42979-025-03770-3","type":"journal-article","created":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T07:10:32Z","timestamp":1740035432000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Automated Assessment of Classroom Interaction Based on Verbal Dynamics: A Deep Learning Approach"],"prefix":"10.1007","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8824-9270","authenticated-orcid":false,"given":"Sadhana","family":"Singh","sequence":"first","affiliation":[]},{"given":"Lotika","family":"Singh","sequence":"additional","affiliation":[]},{"given":"Nandita","family":"Satsangee","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,2,20]]},"reference":[{"key":"3770_CR1","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1016\/j.neunet.2021.03.004","volume":"140","author":"Z Bai","year":"2021","unstructured":"Bai Z, Zhang X. Speaker recognition based on deep learning: an overview. Neural Netw. 2021;140:65\u201399.","journal-title":"Neural Netw"},{"issue":"7","key":"3770_CR2","doi-asserted-by":"publisher","first-page":"451","DOI":"10.3102\/0013189X18785613","volume":"47","author":"S Kelly","year":"2018","unstructured":"Kelly S, Olney AM, Donnelly P, Nystrand M, D\u2019Mello SK. Automatically measuring question authenticity in real-world classrooms. Educ Res. 2018;47(7):451\u201364.","journal-title":"Educ Res"},{"issue":"9","key":"3770_CR3","doi-asserted-by":"publisher","first-page":"4785","DOI":"10.3390\/app12094785","volume":"12","author":"O Sapena","year":"2022","unstructured":"Sapena O, Onaindia E. Multimodal classification of teaching activities from University lecture recordings. Appl Sci. 2022;12(9):4785.","journal-title":"Appl Sci"},{"issue":"2","key":"3770_CR4","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1109\/JSTSP.2019.2908700","volume":"13","author":"H Purwins","year":"2019","unstructured":"Purwins H, Li B, Virtanen T, Schl\u00fcter J, Chang SY, Sainath T. Deep Learning for Audio Signal Processing. IEEE J Sel Top Signal Process. 2019;13(2):206\u201319.","journal-title":"IEEE J Sel Top Signal Process"},{"key":"3770_CR5","unstructured":"Amidon E, Hough J. Interaction analysis: Theory, research and application., 1967."},{"key":"3770_CR6","unstructured":"Hora MT, Oleson A, Ferrare JJ. Teaching dimensions observation protocol (TDOP) user\u2019s manual. Madison Wis Cent Educ Res, 2013."},{"issue":"2","key":"3770_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1187\/cbe.14-06-0095","volume":"14","author":"SL Eddy","year":"2015","unstructured":"Eddy SL, Converse M, Wenderoth MP. PORTAAL: a classroom observation tool assessing evidence-based teaching practices for active learning in large science, technology, engineering, and mathematics classes. CBE Life Sci Educ. 2015;14(2):1\u201316.","journal-title":"CBE Life Sci Educ"},{"key":"3770_CR8","unstructured":"Pianta R, La Paro K, Hamre B. Classroom Assessment Scoring System\u2122: Manual K-3. 2008."},{"issue":"4","key":"3770_CR9","doi-asserted-by":"publisher","first-page":"618","DOI":"10.1187\/cbe.13-08-0154","volume":"12","author":"MK Smith","year":"2013","unstructured":"Smith MK, Jones FHM, Gilbert SL, Wieman CE. The classroom observation protocol for undergraduate stem (COPUS): a new instrument to characterize university STEM classroom practices. CBE Life Sci Educ. 2013;12(4):618\u201327.","journal-title":"CBE Life Sci Educ"},{"key":"3770_CR10","doi-asserted-by":"crossref","unstructured":"Chan M, Ochoa X. D. C.-M. learning paradigms: Advances, and undefined 2020, Multimodal learning analytics in a laboratory classroom, SpringerMCE Chan, X Ochoa, D ClarkeMachine Learn. Paradig. Adv. Learn. Anal. 2020\u2022Springer.","DOI":"10.1007\/978-3-030-13743-4_8"},{"key":"3770_CR11","doi-asserted-by":"crossref","unstructured":"Cyrta P, Trzci\u0144ski T, Stokowiec W. Speaker diarization using deep recurrent convolutional neural networks for speaker embeddings. in Int Conf Inform Syst Archit Technol, 2017, pp. 107\u2013117.","DOI":"10.1007\/978-3-319-67220-5_10"},{"key":"3770_CR12","doi-asserted-by":"crossref","unstructured":"Hr\u00faz M, Zaj\u00edc Z. Convolutional Neural Network for speaker change detection in telephone speaker diarization system, ICASSP, IEEE Int. Conf. Acoust. Speech Signal Process. - Proc. 4945\u20134949, 2017.","DOI":"10.1109\/ICASSP.2017.7953097"},{"key":"3770_CR13","doi-asserted-by":"crossref","unstructured":"Yin R et al. Speaker Change Detection in Broadcast TV using bidirectional long short-term memory networks. InInterspeech 2017. ISCA: pp. 3827\u20133831.","DOI":"10.21437\/Interspeech.2017-65"},{"issue":"1","key":"3770_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-022-11012-2","volume":"12","author":"C Meng","year":"2022","unstructured":"Meng C, Trinh L, Xu N, Enouen J, Liu Y. Interpretability and fairness evaluation of deep learning models on MIMIC-IV dataset. Sci Rep. 2022;12(1):1\u201328.","journal-title":"Sci Rep"},{"key":"3770_CR15","doi-asserted-by":"crossref","unstructured":"Akman A, Schuller BW. Audio Explainable Artificial Intelligence: A Review, 2024.","DOI":"10.34133\/icomputing.0074"},{"issue":"1","key":"3770_CR16","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1016\/j.jfranklin.2023.11.038","volume":"361","author":"S Becker","year":"2024","unstructured":"Becker S, Vielhaben J, Ackermann M, M\u00fcller K-R, Lapuschkin S, Samek W. AudioMNIST: exploring explainable Artificial Intelligence for audio analysis on a simple benchmark. J Frankl Inst. 2024;361(1):418\u201328.","journal-title":"J Frankl Inst"},{"key":"3770_CR17","doi-asserted-by":"crossref","unstructured":"Wang C, Lostanlen V, Lagrange M. Explainable audio Classification of Playing Techniques with Layer-wise Relevance Propagation, in ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023; 1\u20135.","DOI":"10.1109\/ICASSP49357.2023.10095894"},{"key":"3770_CR18","doi-asserted-by":"crossref","unstructured":"Mariotte T, Almud\u00e9var A, Tahon M, Ortega A. An Explainable Proxy Model for Multilabel Audio Segmentation, in ICASSP 2024\u20132024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024, pp. 531\u2013535.","DOI":"10.1109\/ICASSP48485.2024.10446648"},{"key":"3770_CR19","doi-asserted-by":"crossref","unstructured":"Ribeiro MT, Singh S, Guestrin C. \u2018 Why should i trust you?\u2019 Explaining the predictions of any classifier, in Proceedings of the 22nd ACM SIGKDD int. conf. on knowledge discovery and data mining, 2016, pp. 1135\u20131144.","DOI":"10.1145\/2939672.2939778"},{"key":"3770_CR20","doi-asserted-by":"crossref","unstructured":"Carletta J et al. The AMI meeting corpus: a pre-announcement. in Int Workshop Mach Learn Multimodal Interact, Lecture Notes in Computer Science, vol 3869, Springer, Berlin, Heidelberg, 2005; pp. 28\u201339.","DOI":"10.1007\/11677482_3"},{"key":"3770_CR21","unstructured":"Junin A, Edwards J, Gelbart D, York N, THE ICSI MEETING CORPUS \u2019 International Computer Science Institute., Berkeley, CA 3SRI Intemational, Menlo Park, CA, English, pp. 3\u20136, 2003."},{"key":"3770_CR22","doi-asserted-by":"publisher","first-page":"101317","DOI":"10.1016\/j.csl.2021.101317","volume":"72","author":"TJ Park","year":"2022","unstructured":"Park TJ, Kanda N, Dimitriadis D, Han KJ, Watanabe S, Narayanan S. A review of speaker diarization: recent advances with deep learning. Comput Speech Lang. 2022;72:101317.","journal-title":"Comput Speech Lang"},{"issue":"2","key":"3770_CR23","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1109\/TASL.2011.2125954","volume":"20","author":"X Anguera","year":"2012","unstructured":"Anguera X, Bozonnet S, Evans N, Fredouille C, Friedland G, Vinyals O. Speaker diarization: a review of recent research. IEEE Trans Audio Speech Lang Process. 2012;20(2):356\u201370.","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"3770_CR24","doi-asserted-by":"crossref","unstructured":"Otterson S, Ostendorf M. Efficient use of overlap information in speaker diarization, in 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU), 2007, pp. 683\u2013686.","DOI":"10.1109\/ASRU.2007.4430194"},{"key":"3770_CR25","doi-asserted-by":"crossref","unstructured":"Horiguchi S, Garcia P, Fujita Y, Watanabe S, Nagamatsu K. End-to-end speaker diarization as post-processing, in ICASSP 2021\u20132021 IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), 2021; 7188\u20137192.","DOI":"10.1109\/ICASSP39728.2021.9413436"},{"key":"3770_CR26","doi-asserted-by":"crossref","unstructured":"Graves A, Mohamed A, Hinton G. Speech recognition with deep recurrent neural networks, in 2013 IEEE int. conf. on acoustics, speech and signal processing, 2013;6645\u20136649.","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"3770_CR27","doi-asserted-by":"crossref","unstructured":"Sajjan N, Ganesh S, Sharma N, Ganapathy S, Ryant N. Leveraging LSTM models for overlap detection in multi-party meetings, ICASSP, IEEE Int. Conf. Acoust. Speech Signal Process. - Proc. 2018-April; 5249\u20135253, 2018.","DOI":"10.1109\/ICASSP.2018.8462548"},{"key":"3770_CR28","doi-asserted-by":"crossref","unstructured":"James A et al. Automated classification of classroom climate by audio analysis, in 9th Int. Workshop on Spoken Dialogue System Technology, 2019, pp. 41\u201349.","DOI":"10.1007\/978-981-13-9443-0_4"},{"key":"3770_CR29","unstructured":"Ford M, Baer CT, Xu D, Yapanel U, Gray S. The lenatm language environment analysis system, LENA Foundation Technical Report LTR-03-2, 2008."},{"key":"3770_CR30","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/j.compedu.2014.05.010","volume":"78","author":"Z Wang","year":"2014","unstructured":"Wang Z, Pan X, Miller KF, Cortina KS. Automatic classification of activities in classroom discourse. Comput Educ. 2014;78:115\u201323.","journal-title":"Comput Educ"},{"key":"3770_CR31","unstructured":"Worsley M, Blikstein P. What\u2019s an Expert? Using Learning Analytics to Identify Emergent Markers of Expertise through Automated Speech, Sentiment and Sketch Analysis., in EDM, 2011;235\u2013240."},{"key":"3770_CR32","doi-asserted-by":"crossref","unstructured":"Eyben F, W\u00f6llmer M, Schuller B. OpenSMILE - The Munich versatile and fast open-source audio feature extractor, MM\u201910 - Proc. ACM Multimed. 2010 Int. Conf. 1459\u20131462, 2010.","DOI":"10.1145\/1873951.1874246"},{"key":"3770_CR33","unstructured":"Owens MT et al. Classroom sound can be used to classify teaching practices in college science courses, Proc. Natl. Acad. Sci. 2017;114(12);3085\u20133090."},{"key":"3770_CR34","unstructured":"Slyman E, Daw C, Skrabut M, Usenko A, Hutchinson B. Fine-grained classroom activity detection from audio with neural networks, arXiv Prepr. arXiv2107.14369, 2021."},{"key":"3770_CR35","doi-asserted-by":"crossref","unstructured":"Sapena O, Sciences EO-A. and undefined 2022, Multimodal Classification of Teaching Activities from University Lecture Recordings, mdpi.comO Sapena, E OnaindiaApplied Sci. 2022\u2022mdpi.com.","DOI":"10.3390\/app12094785"},{"key":"3770_CR36","first-page":"1","volume":"62","author":"Z Li","year":"2024","unstructured":"Li Z, Xiong F, Zhou J, Lu J, Zhao Z, Qian Y. Material-guided Multiview Fusion Network for Hyperspectral object Tracking. IEEE Trans Geosci Remote Sens. 2024;62:1\u201315.","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"3770_CR37","doi-asserted-by":"publisher","first-page":"2901","DOI":"10.1109\/TIP.2023.3263109","volume":"32","author":"Z Li","year":"2023","unstructured":"Li Z, Xiong F, Zhou J, Lu J, Qian Y. Learning a deep Ensemble Network with Band Importance for Hyperspectral object Tracking. IEEE Trans Image Process. 2023;32:2901\u201314.","journal-title":"IEEE Trans Image Process"},{"key":"3770_CR38","unstructured":"Raj D. Listening to Multi-talker Conversations: Modular and End-to-end Perspectives, 2024."},{"key":"3770_CR39","doi-asserted-by":"crossref","unstructured":"Zhao G, Wang Q, Lu H, Huang Y, Moreno IL. Augmenting transformer-transducer based speaker change detection with token-level training loss, in ICASSP 2023\u20132023 IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), 2023; 1\u20135.","DOI":"10.1109\/ICASSP49357.2023.10094955"},{"key":"3770_CR40","doi-asserted-by":"crossref","unstructured":"Schmidt L, Sharifi M, Moreno IL. Large-scale speaker identification, ICASSP, IEEE Int. Conf. Acoust. Speech Signal Process. - Proc. 2014;1650\u20131654.","DOI":"10.1109\/ICASSP.2014.6853878"},{"key":"3770_CR41","unstructured":"DSHOnline. DSHOnline - YouTube., https:\/\/www.youtube.com\/user\/DSHOnline\/featured"},{"key":"3770_CR42","unstructured":"Meganathan R. Ramanujam Meganathan-YouTube.,https:\/\/www.youtube.com\/user\/kankoduthavanithan"},{"key":"3770_CR43","unstructured":"TrainingAndImpactTFI. TrainingAndImpactTFI - YouTube., https:\/\/www.youtube.com\/@TrainingAndImpactTFI"},{"key":"3770_CR44","first-page":"7124","volume":"2020\u2013May","author":"H Bredin","year":"2020","unstructured":"Bredin H, et al. Pyannote.Audio: neural building blocks for Speaker Diarization. ICASSP IEEE Int Conf Acoust Speech Signal Process - Proc. 2020;2020\u2013May:7124\u20138.","journal-title":"ICASSP IEEE Int Conf Acoust Speech Signal Process - Proc"},{"key":"3770_CR45","doi-asserted-by":"crossref","unstructured":"Han KJ, Narayanan SS. Agglomerative hierarchical speaker clustering using incremental Gaussian mixture cluster modeling., in Interspeech, 2008;20\u201323.","DOI":"10.21437\/Interspeech.2008-3"},{"key":"3770_CR46","doi-asserted-by":"crossref","unstructured":"McFee B et al. librosa: Audio and music signal analysis in python., in SciPy, 2015, pp. 18\u201324.","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"3770_CR47","doi-asserted-by":"crossref","unstructured":"Yin R, Bredin H, Barras C. Speaker change detection in broadcast tv using bidirectional long short-term memory networks, in Interspeech 2017.","DOI":"10.21437\/Interspeech.2017-65"},{"key":"3770_CR48","doi-asserted-by":"crossref","unstructured":"Pandey A, Wang D. TCNN: Temporal convolutional neural network for real-time speech enhancement in the time domain, in ICASSP 2019\u20132019 IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP). 2019;6875\u20136879.","DOI":"10.1109\/ICASSP.2019.8683634"},{"key":"3770_CR49","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1016\/j.neunet.2021.04.020","volume":"141","author":"G Sun","year":"2021","unstructured":"Sun G, Zhang C, Woodland PC. Combination of deep speaker embeddings for diarisation. Neural Netw. 2021;141:372\u201384.","journal-title":"Neural Netw"},{"key":"3770_CR50","doi-asserted-by":"crossref","unstructured":"Raj D, Huang Z, Khudanpur S. Multi-class spectral clustering with overlaps for speaker diarization, in 2021 IEEE Spoken Language Technology Workshop (SLT), 2021;582\u2013589.","DOI":"10.1109\/SLT48900.2021.9383602"},{"key":"3770_CR51","doi-asserted-by":"crossref","unstructured":"Su H et al. A multitask learning framework for speaker change detection with content information from unsupervised speech decomposition, in ICASSP 2022\u20132022 IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP). 2022; 8087\u20138091.","DOI":"10.1109\/ICASSP43922.2022.9746116"},{"key":"3770_CR52","doi-asserted-by":"crossref","unstructured":"Zhao G et al. USM-SCD: Multilingual speaker change detection based on large pretrained foundation models, in ICASSP 2024\u20132024 IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), 2024;11801\u201311805.","DOI":"10.1109\/ICASSP48485.2024.10447263"},{"key":"3770_CR53","unstructured":"Wong A, Wang XY, Hryniowski A. How much can we really trust you? towards simple, interpretable trust quantification metrics for deep neural networks, arXiv Prepr. arXiv 2009.05835, 2020."},{"key":"3770_CR54","unstructured":"Cheng M, Sun T, Nazarian S, Bogdan P. Trustworthiness Evaluation and Trust-Aware Design of Cnn Architectures, Proc. Mach. Learn. Res., vol. 199, no. 2018, pp. 1086\u20131102, 2022."},{"issue":"5","key":"3770_CR55","first-page":"1","volume":"18","author":"F Mukhlis","year":"2024","unstructured":"Mukhlis F, Rokhman I, Zulaeha, Mardikantoro HB. Optimization of teachers\u2019 Verbal Communication Rhetoric in improving the quality of Education services. Rev Gest Soc e Ambient. 2024;18(5):1\u201319.","journal-title":"Rev Gest Soc e Ambient"},{"issue":"2","key":"3770_CR56","first-page":"797","volume":"2","author":"A Novitasari","year":"2023","unstructured":"Novitasari A, Fauziah V, Irmayanti I. Teacher communication style in Achieving Learning Success in the Classroom. AURELIA J Penelit Dan Pengabdi Masy Indones. 2023;2(2):797\u2013802.","journal-title":"AURELIA J Penelit Dan Pengabdi Masy Indones"},{"key":"3770_CR57","doi-asserted-by":"crossref","unstructured":"J\u00e4rvinen K, K\u00e4hk\u00f6nen AL, Nieminen P, M\u00e4ntyl\u00e4 T. Talking like a Teacher\u2014A study of Pre-service teachers\u2019 Voice and Speech characteristics in learning and teaching situations. Educ Sci, 14, 2, 2024.","DOI":"10.3390\/educsci14020210"},{"issue":"3","key":"3770_CR58","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1080\/0022027042000328468","volume":"37","author":"P van Huizen","year":"2005","unstructured":"van Huizen P, van Oers B, Wubbels T. A vygotskian perspective on teacher education. J Curric Stud. 2005;37(3):267\u201390.","journal-title":"J Curric Stud"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-03770-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-025-03770-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-03770-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T07:10:54Z","timestamp":1740035454000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-025-03770-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,20]]},"references-count":58,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,3]]}},"alternative-id":["3770"],"URL":"https:\/\/doi.org\/10.1007\/s42979-025-03770-3","relation":{},"ISSN":["2661-8907"],"issn-type":[{"value":"2661-8907","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,20]]},"assertion":[{"value":"24 September 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 February 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare they have no financial interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Financial Interests"}},{"value":"On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}],"article-number":"201"}}