{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T13:33:48Z","timestamp":1787578428545,"version":"build-2736575974"},"reference-count":35,"publisher":"Association for Computing Machinery (ACM)","issue":"5","license":[{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Science Foundation","award":["1838939, 1934568, and 1937158"],"award-info":[{"award-number":["1838939, 1934568, and 1937158"]}]},{"name":"National Center for Interventional Biophotonic Technologies","award":["1P41EB032840"],"award-info":[{"award-number":["1P41EB032840"]}]},{"name":"University of California-Noyce Initiative"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Embed. Comput. Syst."],"published-print":{"date-parts":[[2026,9,30]]},"abstract":"<jats:p>\n                    Separating sensed signals is a crucial task for many wearable systems, where the acquired data contains a mixture of a target signal of interest and several interfering signals, arising from quasi-periodic physiological phenomena such as cardiac and respiratory activity with slowly varying frequency and amplitude. In practice, the task of separating the signals is challenged by quality and quantity of available physiological data. To overcome this limitation, we propose a novel signal separation technique that can effectively isolate the target signal from a sensed mixed signal, using only a single trace of data. We leverage application-specific attributes of the problem, and approach signal separation as an instance of spectrogram in-painting with a custom-designed generative neural network model. The efficacy of the method is demonstrated in the context of transabdominal fetal pulse oximetry application, using both synthesized and\n                    <jats:italic toggle=\"yes\">in-vivo<\/jats:italic>\n                    data collected from pregnant ovine models. Our approach significantly outperforms prior art, achieving 106% average improvement in signal-to-distortion ratio and 85% reduction in mean squared error in synthesized data, compared to the best competing method. In case of\n                    <jats:italic toggle=\"yes\">in-vivo<\/jats:italic>\n                    data collected in animal experiments, where reference signals are unknown, our method substantially improves performance of a downstream task. Specifically, the proposed method reduces the correlation error in estimated fetal blood oxygen saturation by 80.5% compared to a state of the art technique, showcasing its potential to advance wearable systems.\n                  <\/jats:p>","DOI":"10.1145\/3820374","type":"journal-article","created":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T19:00:39Z","timestamp":1782846039000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DHF: A Generative AI Approach to Data-Efficient Signal Separation for Wearable Embedded Systems"],"prefix":"10.1145","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6643-259X","authenticated-orcid":false,"given":"Mahya","family":"Saffarpour","sequence":"first","affiliation":[{"name":"Electrical and Computer Engineering, University of California Davis","place":["Davis, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4071-6435","authenticated-orcid":false,"given":"Ziyuan","family":"Li","sequence":"additional","affiliation":[{"name":"University of California Davis","place":["Davis, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7165-6715","authenticated-orcid":false,"given":"Kourosh","family":"Vali","sequence":"additional","affiliation":[{"name":"University of California Davis","place":["Davis, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9615-2460","authenticated-orcid":false,"given":"Weitai","family":"Qian","sequence":"additional","affiliation":[{"name":"University of California Davis","place":["Davis, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5894-2883","authenticated-orcid":false,"given":"Begum","family":"Kasap","sequence":"additional","affiliation":[{"name":"University of California Davis","place":["Davis, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1036-791X","authenticated-orcid":false,"given":"Soheil","family":"Ghiasi","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering, University of California, Davis","place":["Davis, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,24]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2731300"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2288675"},{"issue":"1","key":"e_1_3_1_4_2","doi-asserted-by":"crossref","first-page":"1798","DOI":"10.1038\/s41598-023-28390-w","article-title":"Data-driven nonstationary signal decomposition approaches: A comparative analysis","volume":"13","author":"Eriksen Thomas","year":"2023","unstructured":"Thomas Eriksen and Naveed ur Rehman. 2023. Data-driven nonstationary signal decomposition approaches: A comparative analysis. Scientific Reports 13, 1 (2023), 1798.","journal-title":"Scientific Reports"},{"issue":"1","key":"e_1_3_1_5_2","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1109\/TBME.2020.3000977","article-title":"Design and in vivo evaluation of a non-invasive transabdominal fetal pulse oximeter","volume":"68","author":"Fong Daniel D.","year":"2020","unstructured":"Daniel D. Fong, Kaeli J. Yamashiro, Kourosh Vali, Laura A. Galganski, Jameson Thies, Rasta Moeinzadeh, Christopher Pivetti, Andr\u00e9 Knoesen, Vivek J. Srinivasan, Herman L. Hedriana, et\u00a0al. 2020. Design and in vivo evaluation of a non-invasive transabdominal fetal pulse oximeter. IEEE Transactions on Biomedical Engineering 68, 1 (2020), 256\u2013266.","journal-title":"IEEE Transactions on Biomedical Engineering"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/s0029-7844(02)00343-1"},{"key":"e_1_3_1_7_2","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1002\/9781119279860.ch5","article-title":"Spectral masking and filtering","author":"Gerkmann Timo","year":"2018","unstructured":"Timo Gerkmann and Emmanuel Vincent. 2018. Spectral masking and filtering. Audio Source Separation and Speech Enhancement. John Wiley & Sons, 65\u201385.","journal-title":"Audio Source Separation and Speech Enhancement"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1161\/01.CIR.101.23.e215"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2752720"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.1998.0193"},{"key":"e_1_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Yusuf Isik Jonathan Le Roux Zhuo Chen Shinji Watanabe and John R. Hershey. 2016. Single-channel multi-speaker separation using deep clustering. arXiv:1607.02173. Retrieved from https:\/\/arxiv.org\/abs\/1607.02173","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"e_1_3_1_12_2","volume-title":"18th International Society for Music Information Retrieval Conference.","author":"Jansson Andreas","year":"2017","unstructured":"Andreas Jansson, Eric Humphrey, Nicola Montecchio, Rachel Bittner, Aparna Kumar, and Tillman Weyde. 2017. Singing voice separation with deep u-net convolutional networks. In 18th International Society for Music Information Retrieval Conference. (2017)."},{"key":"e_1_3_1_13_2","article-title":"Mimic-iv","author":"Johnson Alistair","year":"2020","unstructured":"Alistair Johnson, Lucas Bulgarelli, Tom Pollard, Steven Horng, Leo Anthony Celi, and Roger Mark. 2020. Mimic-iv. PhysioNet. Retrieved August 23, 2021 from https:\/\/physionet.org\/content\/mimiciv\/1.0\/","journal-title":"PhysioNet"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2023.3238736"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1038\/44565"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952118"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"e_1_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Vivek Narayanaswamy Jayaraman J. Thiagarajan Rushil Anirudh and Andreas Spanias. 2020. Unsupervised audio source separation using generative priors. arXiv:2005.13769. Retrieved from https:\/\/arxiv.org\/abs\/2005.13769","DOI":"10.21437\/Interspeech.2020-3115"},{"key":"e_1_3_1_20_2","article-title":"Electronic fetal monitoring, cerebral palsy, and caesarean section: Assumptions versus evidence","volume":"355","author":"Nelson Karin B.","year":"2016","unstructured":"Karin B. Nelson, Thomas P. Sartwelle, and Dwight J. Rouse. 2016. Electronic fetal monitoring, cerebral palsy, and caesarean section: Assumptions versus evidence. BMJ 355 (2016).","journal-title":"BMJ"},{"issue":"9","key":"e_1_3_1_21_2","doi-asserted-by":"crossref","first-page":"1503","DOI":"10.1016\/j.automatica.2005.04.011","article-title":"Estimation and tracking of complex-valued quasi-periodically varying systems","volume":"41","author":"Nied\u017awiecki Maciej","year":"2005","unstructured":"Maciej Nied\u017awiecki and Piotr Kaczmarek. 2005. Estimation and tracking of complex-valued quasi-periodically varying systems. Automatica 41, 9 (2005), 1503\u20131516.","journal-title":"Automatica"},{"issue":"1","key":"e_1_3_1_22_2","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1109\/TASL.2012.2213249","article-title":"Repeating pattern extraction technique (REPET): A simple method for music\/voice separation","volume":"21","author":"Rafii Zafar","year":"2012","unstructured":"Zafar Rafii and Bryan Pardo. 2012. Repeating pattern extraction technique (REPET): A simple method for music\/voice separation. IEEE Transactions on Audio, Speech, and Language Processing 21, 1 (2012), 73\u201384.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"e_1_3_1_23_2","first-page":"11220","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"36","author":"Rixen Joel","year":"2022","unstructured":"Joel Rixen and Matthias Renz. 2022. Sfsrnet: Super-resolution for single-channel audio source separation. In Proceedings of the AAAI Conference on Artificial Intelligence 36 (2022), 11220\u201311228."},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_1_25_2","volume-title":"Proceedings of the 2024 61st ACM\/IEEE Design Automation Conference (DAC)","author":"Saffarpour Mahya","year":"2024","unstructured":"Mahya Saffarpour, Kourosh Vali, Weitai Qian, Begum Kasap, Diana L. Farmer, Aijun Wang, and Soheil Ghiasi. 2024. Deep harmonic finesse: Signal separation in wearable systems with limited data. In Proceedings of the 2024 61st ACM\/IEEE Design Automation Conference (DAC). IEEE."},{"key":"e_1_3_1_26_2","volume-title":"Proceedings of the 2024 Design, Automation & Test in Europe Conference & Exhibition (DATE)","author":"Saffarpour Mahya","year":"2024","unstructured":"Mahya Saffarpour, Kourosh Vali, Weitai Qian, Begum Kasap, Diana L. Farmer, Aijun Wang, and Soheil Ghiasi. 2024. Deep quasi-periodic priors: Signal separation in wearable systems with limited data. In Proceedings of the 2024 Design, Automation & Test in Europe Conference & Exhibition (DATE). IEEE."},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/s0735-6757(99)90019-0"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-26951-z"},{"key":"e_1_3_1_29_2","volume-title":"IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)","author":"Stoller Daniel","year":"2018","unstructured":"Daniel Stoller, Sebastian Ewert, and Simon Dixon. 2018. Wave-u-net: A multi-scale neural network for end-to-end audio source separation. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)."},{"key":"e_1_3_1_30_2","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","author":"Tian Yapeng","year":"2020","unstructured":"Yapeng Tian, Chenliang Xu, and Dingzeyu Li. 2020. Deep audio prior: Learning sound source separation from a single audio mixture. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops."},{"key":"e_1_3_1_31_2","volume-title":"International Conference on Learning Representations.","author":"Tzinis Efthymios","year":"2020","unstructured":"Efthymios Tzinis, Scott Wisdom, Aren Jansen, Shawn Hershey, Tal Remez, Daniel PW Ellis, and John R. Hershey. 2020. Into the wild with audioscope: Unsupervised audio-visual separation of on-screen sounds.In International Conference on Learning Representations."},{"key":"e_1_3_1_32_2","first-page":"9446","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Ulyanov Dmitry","year":"2018","unstructured":"Dmitry Ulyanov, Andrea Vedaldi, and Victor Lempitsky. 2018. Deep image prior. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 9446\u20139454."},{"key":"e_1_3_1_33_2","first-page":"1100","volume-title":"Proceedings of the 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)","author":"Vali Kourosh","year":"2021","unstructured":"Kourosh Vali, Begum Kasap, Weitai Qian, Ata Vafi, Mahya Saffarpour, and Soheil Ghiasi. 2021. Estimation of fetal blood oxygen saturation from transabdominally acquired photoplethysmogram waveforms. In Proceedings of the 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). IEEE, 1100\u20131103."},{"key":"e_1_3_1_34_2","first-page":"3846","article-title":"Unsupervised sound separation using mixture invariant training","volume":"33","author":"Wisdom Scott","year":"2020","unstructured":"Scott Wisdom, Efthymios Tzinis, Hakan Erdogan, Ron Weiss, Kevin Wilson, and John Hershey. 2020. Unsupervised sound separation using mixture invariant training. Advances in Neural Information Processing Systems 33 (2020), 3846\u20133857.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2531285"},{"key":"e_1_3_1_36_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Zhang Zhoutong","year":"2019","unstructured":"Zhoutong Zhang, Yunyun Wang, Chuang Gan, Jiajun Wu, Joshua B. Tenenbaum, Antonio Torralba, and William T. Freeman. 2019. Deep audio priors emerge from harmonic convolutional networks. In Proceedings of the International Conference on Learning Representations."}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3820374","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T13:07:25Z","timestamp":1787576845000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3820374"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,24]]},"references-count":35,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,9,30]]}},"alternative-id":["10.1145\/3820374"],"URL":"https:\/\/doi.org\/10.1145\/3820374","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"value":"1539-9087","type":"print"},{"value":"1558-3465","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,24]]},"assertion":[{"value":"2025-07-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-30","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}