{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T17:24:27Z","timestamp":1769621067686,"version":"3.49.0"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032130242","type":"print"},{"value":"9783032130228","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\/978-3-032-13022-8_23","type":"book-chapter","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T04:31:12Z","timestamp":1769574672000},"page":"331-346","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Machine Learning Pipeline for\u00a0Biofeedback-Driven, Self-guided Virtual Reality Therapy Using Speech-Based Arousal Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5166-8464","authenticated-orcid":false,"given":"Ruth","family":"Amey","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6774-0041","authenticated-orcid":false,"given":"Muhammad Arifur","family":"Rahman","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1677-7485","authenticated-orcid":false,"given":"David J.","family":"Brown","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4559-815X","authenticated-orcid":false,"given":"Matthew C.","family":"Harris","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2082-9070","authenticated-orcid":false,"given":"Nicholas","family":"Shopland","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2037-8348","authenticated-orcid":false,"given":"Mufti","family":"Mahmud","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6631-008X","authenticated-orcid":false,"given":"Samantha","family":"Hilton","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2414-8854","authenticated-orcid":false,"given":"Nadja","family":"Heym","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4333-8442","authenticated-orcid":false,"given":"Alexander","family":"Sumich","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,29]]},"reference":[{"key":"23_CR1","doi-asserted-by":"publisher","unstructured":"Ahammed, M., et al.: Speech emotion recognition: an empirical analysis of machine learning algorithms across diverse data sets. In: Mahmud, M., Ben-Abdallah, H., Kaiser, M.S., Ahmed, M.R., Zhong, N. (eds.) Applied Intelligence and Informatics, AII 2023. CCIS, vol. 2065, pp. 32\u201346. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-68639-9_3","DOI":"10.1007\/978-3-031-68639-9_3"},{"key":"23_CR2","unstructured":"Arushi, Dillon, R., Teoh, A., Dillon, D.: Voice analysis for stress detection and application in virtual reality to improve public speaking in real-time. arXiv arXiv.org (2022)"},{"key":"23_CR3","doi-asserted-by":"publisher","unstructured":"Biswas, M., Kaiser, M., Mahmud, M., Al\u00a0Mamun, S., Hossain, M., Rahman, M.: An XAI based autism detection: the context behind the detection. In: Mahmud, M., Kaiser, M., Vassanelli, S., Dai, Q., Zhong, N. (eds.) Proceedings of the Brain Informatics. LNAI, vol. 12960, pp. 448\u2013459. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86993-9_40","DOI":"10.1007\/978-3-030-86993-9_40"},{"key":"23_CR4","doi-asserted-by":"publisher","unstructured":"Biswas, P., et al.: A nonparametric model for forecasting life expectancy at birth using Gaussian process. In: Mahmud, M., Ieracitano, C., Kaiser, M.S., Mammone, N., Morabito, F.C. (eds.) Applied Intelligence and Informatics. AII 2022. Communications in Computer and Information Science, vol. 1724, pp. 102\u2013116. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-24801-6_8","DOI":"10.1007\/978-3-031-24801-6_8"},{"issue":"4","key":"23_CR5","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1109\/TAFFC.2014.2336244","volume":"5","author":"H Cao","year":"2014","unstructured":"Cao, H., Cooper, D.G., Keutmann, M.K., Gur, R.C., Nenkova, A., Verma, R.: CREMA-D: crowd-sourced emotional multimodal actors dataset. IEEE Trans. Affect. Comput. 5(4), 377\u2013390 (2014)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Dillon, R., Teoh, A.N., et\u00a0al.: Real-time stress detection model and voice analysis: an integrated VR-based game for training public speaking skills. In: 2021 IEEE Conference on Games (CoG), pp.\u00a01\u20134. IEEE (2021)","DOI":"10.1109\/CoG52621.2021.9618989"},{"key":"23_CR7","unstructured":"Dupuis, K., Pichora-Fuller, K.: Toronto Emotional Speech Set (TESS). University of Toronto, Psychology Department (2010)"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Gupta, R.: View of detecting emotions in audio data of patients with post traumatic stress disorder using convolutional neural networks. jsr.org (2023)","DOI":"10.47611\/jsrhs.v12i3.4776"},{"key":"23_CR9","unstructured":"Jackson, P., Haq, S.: Surrey Audio-Visual Expressed Emotion (SAVEE) database. University of Surrey, Guildford, UK (2014)"},{"key":"23_CR10","doi-asserted-by":"publisher","unstructured":"Jothimani, S., Premalatha, K.: MFF-SAug: multi feature fusion with spectrogram augmentation of speech emotion recognition using convolution neural network. Chaos Solitons Fractals (2022). https:\/\/doi.org\/10.1016\/j.chaos.2022.112512","DOI":"10.1016\/j.chaos.2022.112512"},{"issue":"5","key":"23_CR11","doi-asserted-by":"publisher","first-page":"e0196391","DOI":"10.1371\/journal.pone.0196391","volume":"13","author":"SR Livingstone","year":"2018","unstructured":"Livingstone, S.R., Russo, F.A.: The Ryerson audio-visual database of emotional speech and song (RAVDESS): a dynamic, multimodal set of facial and vocal expressions in North American English. PLoS ONE 13(5), e0196391 (2018)","journal-title":"PLoS ONE"},{"key":"23_CR12","doi-asserted-by":"publisher","unstructured":"Mahmud, M., et\u00a0al.: Towards explainable and privacy-preserving artificial intelligence for personalisation in autism spectrum disorder. In: Antona, M., Stephanidis, C. (eds.) International Conference on Human-Computer Interaction, HCII 2022, vol. 3309, pp. 356\u2013370. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-05039-8_26","DOI":"10.1007\/978-3-031-05039-8_26"},{"key":"23_CR13","doi-asserted-by":"publisher","unstructured":"Mizan, M.B., et al.: Dimensionality reduction in handwritten digit recognition. In: Mahmud, M., Mendoza-Barrera, C., Kaiser, M.S., Bandyopadhyay, A., Ray, K., Lugo, E. (eds.) Proceedings of Trends in Electronics and Health Informatics, pp. 35\u201350. Springer Nature Singapore, Singapore (2023). https:\/\/doi.org\/10.1007\/978-981-99-1916-1_3","DOI":"10.1007\/978-981-99-1916-1_3"},{"key":"23_CR14","doi-asserted-by":"publisher","unstructured":"Nasrin, F., Ahmed, N.I., Rahman, M.A.: Auditory attention state decoding for the quiet and hypothetical environment: a comparison between bLSTM and SVM. In: Kaiser, M.S., Bandyopadhyay, A., Mahmud, M., Ray, K. (eds.) Proceedings of TCCE, pp. 291\u2013301. Advances in Intelligent Systems and Computing, Springer, Singapore (2021). https:\/\/doi.org\/10.1007\/978-981-33-4673-4_23","DOI":"10.1007\/978-981-33-4673-4_23"},{"key":"23_CR15","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.apacoust.2018.08.003","volume":"142","author":"T \u00d6zseven","year":"2018","unstructured":"\u00d6zseven, T.: Investigation of the effect of spectrogram images and different texture analysis methods on speech emotion recognition. Appl. Acoust. 142, 70\u201377 (2018)","journal-title":"Appl. Acoust."},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Premkumar, P., et al.: Augmenting self-guided virtual-reality exposure therapy for social anxiety with biofeedback: a randomised controlled trial. Front. Psych. 15, 1467141 (2024)","DOI":"10.3389\/fpsyt.2024.1467141"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Rahman, M.A., et\u00a0al.: Biofeedback towards machine learning driven self-guided virtual reality exposure therapy based on arousal state detection from multimodal data (2022)","DOI":"10.21203\/rs.3.rs-2152608\/v1"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Rahman, M.A., et al.: Enhancing biofeedback-driven self-guided virtual reality exposure therapy through arousal detection from multimodal data using machine learning. Brain Inf. 10(1), 14 (2023)","DOI":"10.1186\/s40708-023-00193-9"},{"key":"23_CR19","doi-asserted-by":"publisher","unstructured":"Rahman, M.A., Brown, D.J., Shopland, N., Burton, A., Mahmud, M.: Explainable multimodal machine learning for engagement analysis by continuous performance test. In: Antona, M., Stephanidis, C. (eds.) Universal Access in Human-Computer Interaction. User and Context Diversity. LNCS, pp. 386\u2013399. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-05039-8_28","DOI":"10.1007\/978-3-031-05039-8_28"},{"key":"23_CR20","doi-asserted-by":"publisher","unstructured":"Rahman, M.A., et\u00a0al.: Towards machine learning driven self-guided virtual reality exposure therapy based on arousal state detection from multimodal data. In: International Conference on Brain Informatics, vol. 13406, pp. 195\u2013209. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-15037-1_17","DOI":"10.1007\/978-3-031-15037-1_17"},{"key":"23_CR21","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1007\/978-3-030-86993-9_34","volume-title":"Brain Informatics","author":"AB Rakib","year":"2021","unstructured":"Rakib, A.B., Rumky, E.A., Ashraf, A.J., Hillas, M.M., Rahman, M.A.: Mental healthcare chatbot using sequence-to-sequence learning and\u00a0BiLSTM. In: Mahmud, M., Kaiser, M.S., Vassanelli, S., Dai, Q., Zhong, N. (eds.) BI 2021. LNCS (LNAI), vol. 12960, pp. 378\u2013387. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86993-9_34"},{"issue":"7","key":"23_CR22","first-page":"37","volume":"15","author":"KM Rezaul","year":"2024","unstructured":"Rezaul, K.M., et al.: Enhancing audio classification through MFCC feature extraction and data augmentation with CNN and RNN models. Int. J. Adv. Comput. Sci. Appl. 15(7), 37\u201353 (2024)","journal-title":"Int. J. Adv. Comput. Sci. Appl."}],"container-title":["Lecture Notes in Computer Science","HCI International 2025 \u2013 Late Breaking Papers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-13022-8_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T04:31:14Z","timestamp":1769574674000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-13022-8_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032130242","9783032130228"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-13022-8_23","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":"29 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"HCII","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Human-Computer Interaction","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Gothenburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","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 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"hcii2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2025.hci.international\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}