{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T11:23:22Z","timestamp":1769685802846,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","funder":[{"name":"UKRI","award":["EP\/S02266X\/1"],"award-info":[{"award-number":["EP\/S02266X\/1"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,13]]},"DOI":"10.1145\/3716553.3750753","type":"proceedings-article","created":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T13:13:16Z","timestamp":1760188396000},"page":"87-95","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["From Speech and PPG to EDA: Stress Detection Based on Cross-Modal Fine-Tuning of Foundation Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2504-2798","authenticated-orcid":false,"given":"Alia","family":"Ahmed Al Dossary","sequence":"first","affiliation":[{"name":"School of Computing Science, University of Glasgow, Glasgow, Scotland, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9858-6844","authenticated-orcid":false,"given":"Mathieu","family":"Chollet","sequence":"additional","affiliation":[{"name":"School of Computing Science, University of Glasgow, Glasgow, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9048-0524","authenticated-orcid":false,"given":"Alessandro","family":"Vinciarelli","sequence":"additional","affiliation":[{"name":"School of Computing Science, University of Glasgow, Glasgow, Scotland, United Kingdom"}]}],"member":"320","published-online":{"date-parts":[[2025,10,12]]},"reference":[{"key":"e_1_3_3_2_2_2","volume-title":"Large-scale training of foundation models for wearable biosignals","author":"Abbaspourazad S.","year":"2023","unstructured":"S. Abbaspourazad, O. Elachqar, A.C. Miller, S. Emrani, U. Nallasamy, and I. Shapiro. 2023. Large-scale training of foundation models for wearable biosignals. Technical Report arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.05409."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"J. Allen. 2007. Photoplethysmography and its application in clinical physiological measurement. Physiological Measurement 28 3 (2007).","DOI":"10.1088\/0967-3334\/28\/3\/R01"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"M. Alshamrani. 2021. An advanced stress detection approach based on processing data from wearable wrist devices. International Journal of Advanced Computer Science and Applications 12 7 (2021).","DOI":"10.14569\/IJACSA.2021.0120745"},{"key":"e_1_3_3_2_5_2","volume-title":"GSR analysis for stress: Development and validation of an open source tool for noisy naturalistic gsr data","author":"Aqajari S.A.H.","year":"2020","unstructured":"S.A.H. Aqajari, E.K. Naeini, M.A. Mehrabadi, S. Labbaf, A.M. Rahmani, and N. Dutt. 2020. GSR analysis for stress: Development and validation of an open source tool for noisy naturalistic gsr data. Technical Report arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2005.01834."},{"key":"e_1_3_3_2_6_2","first-page":"12449","volume-title":"Advances in Neural Information Processing Systems","author":"Baevski A.","year":"2020","unstructured":"A. Baevski, Y. Zhou, A. Mohamed, and M. Auli. 2020. wav2vec 2.0: A framework for self-supervised learning of speech representations. In Advances in Neural Information Processing Systems. 12449\u201312460."},{"key":"e_1_3_3_2_7_2","volume-title":"On the Opportunities and Risks of Foundation Models","author":"al. Bommasani, R. and Hudson, D.A. et","year":"2022","unstructured":"Bommasani, R. and Hudson, D.A. et al.2022. On the Opportunities and Risks of Foundation Models. Technical Report."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.5555\/2815662"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"T. Chaspari A. Tsiartas L.I. Stein S.A. Cermak and S.S. Narayanan. 2014. Sparse representation of electrodermal activity with knowledge-driven dictionaries. IEEE Transactions on Biomedical Engineering 62 3 (2014) 960\u2013971.","DOI":"10.1109\/TBME.2014.2376960"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"S. Chen C. Wang Z. Chen Y. Wu S. Liu Z. Chen J. Li N. Kanda T. Yoshioka X. Xiao J. Wu L. Zhou S. Ren Y. Qian Y. Qian J. Wu M. Zeng X. Yu and F. Wei. 2022. WavLM: Large-scale self-supervised pre-training for full stack speech processing. IEEE Journal of Selected Topics in Signal Processing 16 6 (2022) 1505\u20131518.","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"e_1_3_3_2_11_2","volume-title":"Assessing Foundation Models\u2019 Transferability to Physiological Signals in Precision Medicine","author":"Christenson M.","year":"2024","unstructured":"M. Christenson, C. Geary, B. Locke, P. Koirala, and W.W. Pettine. 2024. Assessing Foundation Models\u2019 Transferability to Physiological Signals in Precision Medicine. Technical Report arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.03427."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546396.007"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"crossref","unstructured":"C. Ding Z. Guo Z. Chen R.J. Lee C. Rudin and X. Hu. 2024. SiamQuality: a ConvNet-based foundation model for photoplethysmography signals. Physiological Measurement 45 8 (2024) 085004.","DOI":"10.1088\/1361-6579\/ad6747"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP63861.2024.10800253"},{"key":"e_1_3_3_2_16_2","first-page":"163","volume-title":"A Handbook of Process Tracing Methods for Decision Research: A Critical Review and User\u2019s Guide","author":"Figner B.","year":"2011","unstructured":"B. Figner and R.O. Murphy. 2011. Using skin conductance in judgment and decision making research. In A Handbook of Process Tracing Methods for Decision Research: A Critical Review and User\u2019s Guide. Psychology Press, 163\u2013184."},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM55620.2022.9995093"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"W.-N. Hsu B. Bolte Y.-H.H. Tsai K. Lakhotia R. Salakhutdinov and A. Mohamed. 2021. Hubert: Self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM Transactions on Audio Speech and Language Processing 29 (2021) 3451\u20133460.","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"T. Iqbal P. Redon-Lurbe A.J. Simpkin A. Elahi S. Ganly W. Wijns and A. Shahzad. 2021. A sensitivity analysis of biophysiological responses of stress for wearable sensors in connected health. IEEE Access 9 (2021) 93567\u201393579.","DOI":"10.1109\/ACCESS.2021.3082423"},{"key":"e_1_3_3_2_20_2","first-page":"1","volume-title":"Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society","author":"Kamson A.P.","year":"2024","unstructured":"A.P. Kamson, A.V. Sawant, P.K. Ghosh, and S.S. Jeevannavar. 2024. Exploring Wav2vec 2.0 Model for Heart Sound Analysis. In Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 1\u20135."},{"key":"e_1_3_3_2_21_2","volume-title":"Adam: A method for stochastic optimization","author":"Kingma D.P.","year":"2014","unstructured":"D.P. Kingma and J. Ba. 2014. Adam: A method for stochastic optimization. Technical Report arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1412.6980."},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"A. Liapis E. Faliagka C.P. Antonopoulos G. Keramidas and N. Voros. 2021. Advancing stress detection methodology with deep learning techniques targeting UX evaluation in aal scenarios: Applying embeddings for categorical variables. Electronics 10 13 (2021) 1550.","DOI":"10.3390\/electronics10131550"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1101\/2024.12.18.629057"},{"key":"e_1_3_3_2_25_2","volume-title":"Pre-Trained Foundation Model representations to uncover Breathing patterns in Speech","author":"Mitra V.","year":"2024","unstructured":"V. Mitra, A. Chatterjee, K. Zhai, H. Weng, A. Hill, N. Hay, C. Webb, J. Cheng, and E. Azemi. 2024. Pre-Trained Foundation Model representations to uncover Breathing patterns in Speech. Technical Report arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.13035."},{"key":"e_1_3_3_2_26_2","volume-title":"The effect of person-specific biometrics in improving generic stress predictive models","author":"Nkurikiyeyezu K.","year":"2019","unstructured":"K. Nkurikiyeyezu, A. Yokokubo, and G. Lopez. 2019. The effect of person-specific biometrics in improving generic stress predictive models. Technical Report arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1910.01770."},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"N. Otsu. 1979. A threshold selection method from gray-level histograms. IEEE Transactions on Systems Man and Cybernetics 9 1 (1979) 62\u201366.","DOI":"10.1109\/TSMC.1979.4310076"},{"key":"e_1_3_3_2_28_2","volume-title":"Carbon Emissions and Large Neural Network Training","author":"Patterson D.","year":"2021","unstructured":"D. Patterson, J. Gonzalez, Q. Le, C. Liang, L.-M. Lluis-Miquel\u00a0Munguia, D. Rothchild, D. So, M. Texier, and J. Dean. 2021. Carbon Emissions and Large Neural Network Training. Technical Report arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2104.10350."},{"key":"e_1_3_3_2_29_2","volume-title":"Beyond Speech and More: Investigating the Emergent Ability of Speech Foundation Models for Classifying Physiological Time-Series Signals","author":"Phukan O.C.","year":"2024","unstructured":"O.C. Phukan, S.R. Behera, M.M. Akhtar, A.B. Buduru, and R. Sharma. 2024. Beyond Speech and More: Investigating the Emergent Ability of Speech Foundation Models for Classifying Physiological Time-Series Signals. Technical Report arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.12645."},{"key":"e_1_3_3_2_30_2","volume-title":"PaPaGei: Open Foundation Models for Optical Physiological Signals","author":"Pillai A.","year":"2024","unstructured":"A. Pillai, D. Spathis, F. Kawsar, and M. Malekzadeh. 2024. PaPaGei: Open Foundation Models for Optical Physiological Signals. Technical Report arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.20542."},{"key":"e_1_3_3_2_31_2","first-page":"28492","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Radford A.","year":"2023","unstructured":"A. Radford, J.W. Kim, T. Xu, G. Brockman, C. McLeavey, and I. Sutskever. 2023. Robust speech recognition via large-scale weak supervision. In Proceedings of the International Conference on Machine Learning. 28492\u201328518."},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3242985"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1002\/9781118706664"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3341162.3344831"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"S. Subramanian P.L. Purdon R. Barbieri and E.N. Brown. 2021. A model-based framework for assessing the physiologic structure of electrodermal activity. IEEE Transactions on Biomedical Engineering 68 9 (2021) 2833\u20132845.","DOI":"10.1109\/TBME.2021.3071366"},{"key":"e_1_3_3_2_36_2","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Woo G.","year":"2024","unstructured":"G. Woo, C. Liu, A. Kumar, C. Xiong, S. Savarese, and D. Sahoo. 2024. Unified training of universal time series forecasting transformers. In Proceedings of the International Conference on Machine Learning. Article 2178."},{"key":"e_1_3_3_2_37_2","volume-title":"Advances in Neural Information Processing Systems","author":"Yang C.","year":"2023","unstructured":"C. Yang, M. Westover, and J. Sun. 2023. BIOT: Biosignal transformer for cross-data learning in the wild. In Advances in Neural Information Processing Systems , Vol.\u00a036."},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45855.2022.9838970"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/MeMeA54994.2022.9856558"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"crossref","unstructured":"L. Zhu P. Spachos P.C. Ng Y. Yu Y. Wang K. Plataniotis and D. Hatzinakos. 2023. Stress detection through wrist-based electrodermal activity monitoring and machine learning. IEEE Journal of Biomedical and Health Informatics 27 5 (2023) 2155\u20132165.","DOI":"10.1109\/JBHI.2023.3239305"}],"event":{"name":"ICMI '25: International Conference on Multimodal Interaction","location":"Canberra Australia","acronym":"ICMI '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 27th International Conference on Multimodal Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3716553.3750753","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T22:27:29Z","timestamp":1769466449000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3716553.3750753"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":39,"alternative-id":["10.1145\/3716553.3750753","10.1145\/3716553"],"URL":"https:\/\/doi.org\/10.1145\/3716553.3750753","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]},"assertion":[{"value":"2025-10-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}