{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T14:28:06Z","timestamp":1778336886735,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,11,6]],"date-time":"2022-11-06T00:00:00Z","timestamp":1667692800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-2050910, ECCS-2028872"],"award-info":[{"award-number":["CNS-2050910, ECCS-2028872"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,11,6]]},"DOI":"10.1145\/3560905.3568508","type":"proceedings-article","created":{"date-parts":[[2023,1,24]],"date-time":"2023-01-24T23:37:10Z","timestamp":1674603430000},"page":"149-163","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Hearing Heartbeat from Voice"],"prefix":"10.1145","author":[{"given":"Chenhan","family":"Xu","sequence":"first","affiliation":[{"name":"University at Buffalo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyu","family":"Chen","sequence":"additional","affiliation":[{"name":"University at Buffalo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huining","family":"Li","sequence":"additional","affiliation":[{"name":"University at Buffalo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Gherardi","sequence":"additional","affiliation":[{"name":"University at Buffalo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michelle","family":"Weng","sequence":"additional","affiliation":[{"name":"University at Buffalo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengxiong","family":"Li","sequence":"additional","affiliation":[{"name":"University of Colorado Denver"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenyao","family":"Xu","sequence":"additional","affiliation":[{"name":"University at Buffalo"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,1,24]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Voice user interface market size, share and analysis: Forecast -","author":"Borasi P.","year":"2030","unstructured":"P. Borasi, H. Jangra, and V. Kumar, \"Voice user interface market size, share and analysis: Forecast - 2030.\" [Online]. Available: https:\/\/www.alliedmarketresearch.com\/voice-user-interface-market-A12381"},{"key":"e_1_3_2_1_2_1","volume-title":"Citeseer","author":"Bonastre J.-F.","year":"2003","unstructured":"J.-F. Bonastre, F. Bimbot, L.-J. Bo\u00eb, J. P. Campbell, D. A. Reynolds, and I. Magrin-Chagnolleau, \"Person authentication by voice: A need for caution,\" in Eighth European Conference on Speech Communication and Technology. Citeseer, 2003."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2420950.2420976"},{"key":"e_1_3_2_1_4_1","first-page":"2062","volume-title":"IEEE","author":"Wang Q.","year":"2019","unstructured":"Q. Wang, X. Lin, M. Zhou, Y. Chen, C. Wang, Q. Li, and X. Luo, \"Voicepop: A pop noise based anti-spoofing system for voice authentication on smartphones,\" in IEEE INFOCOM 2019-IEEE Conference on Computer Communications. IEEE, 2019, pp. 2062--2070."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"C. Breazeal \"Emotion and sociable humanoid robots \" International journal of human-computer studies vol. 59 no. 1--2 pp. 119--155 2003.","DOI":"10.1016\/S1071-5819(03)00018-1"},{"key":"e_1_3_2_1_6_1","first-page":"1","volume-title":"Computing, Cybersecurity, and Informatics (CCCI)","author":"Hassan A.","year":"2020","unstructured":"A. Hassan, I. Shahin, and M. B. Alsabek, \"Covid-19 detection system using recurrent neural networks,\" in 2020 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI), 2020, pp. 1--5."},{"key":"e_1_3_2_1_7_1","first-page":"1","volume-title":"Pdvocal: Towards privacy-preserving parkinson's disease detection using non-speech body sounds,\" in The 25th Annual International Conference on Mobile Computing and Networking","author":"Zhang H.","year":"2019","unstructured":"H. Zhang, C. Song, A. Wang, C. Xu, D. Li, and W. Xu, \"Pdvocal: Towards privacy-preserving parkinson's disease detection using non-speech body sounds,\" in The 25th Annual International Conference on Mobile Computing and Networking, 2019, pp. 1--16."},{"key":"e_1_3_2_1_8_1","first-page":"7219","volume-title":"Speech and Signal Processing. IEEE","author":"Schuller B.","year":"2013","unstructured":"B. Schuller, F. Friedmann, and F. Eyben, \"Automatic recognition of physiological parameters in the human voice: Heart rate and skin conductance,\" in 2013 IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE, 2013, pp. 7219--7223."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Z. Zhang \"Mechanics of human voice production and control \" The journal of the acoustical society of america vol. 140 no. 4 pp. 2614--2635 2016.","DOI":"10.1121\/1.4964509"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.4807639"},{"key":"e_1_3_2_1_11_1","volume-title":"Pulmonary circulation: diseases and their treatment","author":"Peacock A. J.","year":"2016","unstructured":"A. J. Peacock, R. Naeije, and L. J. Rubin, Pulmonary circulation: diseases and their treatment. CRC Press, 2016."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1088\/0967-3334\/20\/3\/301"},{"key":"e_1_3_2_1_13_1","volume-title":"Simultaneous assessment of diameter and pressure waveforms in the carotid artery,\" Ultrasound in medicine & biology","author":"Meinders J. M.","unstructured":"J. M. Meinders and A. P. Hoeks, \"Simultaneous assessment of diameter and pressure waveforms in the carotid artery,\" Ultrasound in medicine & biology, vol. 30, no. 2, pp. 147--154, 2004."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.2047107"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-020-00777-8"},{"key":"e_1_3_2_1_16_1","volume-title":"Acoustic theory of speech production","author":"Fant G.","year":"1970","unstructured":"G. Fant, Acoustic theory of speech production. Walter de Gruyter, 1970, no. 2."},{"key":"e_1_3_2_1_17_1","first-page":"1992","volume-title":"IEEE International Conference on Acoustics, Speech, and Signal Processing","volume":"7","author":"Laine U.","year":"1982","unstructured":"U. Laine, \"Modelling of lip radiation impedance in z-domain,\" in ICASSP'82. IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 7. IEEE, 1982, pp. 1992--1995."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1080\/14015430701855333"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.424266"},{"issue":"2","key":"e_1_3_2_1_20_1","first-page":"3","article-title":"Glottal wave analysis with pitch synchronous iterative adaptive inverse filtering","volume":"11","author":"Alku P.","year":"1992","unstructured":"P. Alku, \"Glottal wave analysis with pitch synchronous iterative adaptive inverse filtering,\" Speech communication, vol. 11, no. 2--3, pp. 109--118, 1992.","journal-title":"Speech communication"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1075\/cilt.319.07yeo"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163429"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447582"},{"key":"e_1_3_2_1_24_1","volume-title":"Deep convolutional neural network design patterns,\" arXiv preprint arXiv:1611.00847","author":"Smith L. N.","year":"2016","unstructured":"L. N. Smith and N. Topin, \"Deep convolutional neural network design patterns,\" arXiv preprint arXiv:1611.00847, 2016."},{"key":"e_1_3_2_1_25_1","first-page":"4681","article-title":"Photo-realistic single image super-resolution using a generative adversarial network","author":"Ledig C.","year":"2017","unstructured":"C. Ledig, L. Theis, F. Husz\u00e1r, J. Caballero, A. Cunningham, A. Acosta, A. Aitken, A. Tejani, J. Totz, Z. Wang et al., \"Photo-realistic single image super-resolution using a generative adversarial network,\" in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 4681--4690.","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419982"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.09.024"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.03.013"},{"key":"e_1_3_2_1_29_1","first-page":"5998","volume-title":"Attention is all you need,\" in Advances in neural information processing systems","author":"Vaswani A.","year":"2017","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, \u0141. Kaiser, and I. Polosukhin, \"Attention is all you need,\" in Advances in neural information processing systems, 2017, pp. 5998--6008."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2014.09.005"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2005.09.010"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2010.2045498"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1152\/ajplegacy.1962.203.6.1141"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2018.03.003"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2015.02.012"},{"issue":"1","key":"e_1_3_2_1_36_1","first-page":"64","article-title":"Respiration and heart rate variability: A review with special reference to its application in aerospace medicine","volume":"48","author":"Tripatbi K.","year":"2004","unstructured":"K. Tripatbi, \"Respiration and heart rate variability: A review with special reference to its application in aerospace medicine,\" Indian Journal of Aerospace Medicine, vol. 48, no. 1, pp. 64--75, 2004.","journal-title":"Indian Journal of Aerospace Medicine"},{"key":"e_1_3_2_1_37_1","first-page":"3150","article-title":"How much deep learning does neural style transfer really need? an ablation study","author":"Du L.","year":"2020","unstructured":"L. Du, \"How much deep learning does neural style transfer really need? an ablation study,\" in Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2020, pp. 3150--3159.","journal-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision"},{"key":"e_1_3_2_1_38_1","unstructured":"\"Uma-8 usb mic array - v2.0.\" [Online]. Available: https:\/\/www.minidsp.com\/products\/usb-audio-interface\/uma-8-microphone-array"},{"key":"e_1_3_2_1_39_1","unstructured":"P. Sampson. (2021 Dec) How audacity noise reduction works. [Online]. Available: https:\/\/wiki.audacityteam.org\/wiki\/How_Audacity_Noise_Reduction_Works#artifacts"},{"key":"e_1_3_2_1_40_1","first-page":"1862","volume-title":"ARTICLE","author":"Gilloire A.","year":"1992","unstructured":"A. Gilloire and M. Vetterli, \"Adaptive filtering in sub-bands with critical sampling: analysis, experiments, and application to acoustic echo cancellation,\" IEEE transactions on signal processing, vol. 40, no. ARTICLE, pp. 1862--1875, 1992."},{"key":"e_1_3_2_1_41_1","first-page":"541","volume-title":"IEEE","author":"Jain A.","year":"2015","unstructured":"A. Jain, B. Klare, and A. Ross, \"Guidelines for best practices in biometrics research,\" in 2015 International Conference on Biometrics (ICB). IEEE, 2015, pp. 541--545."},{"key":"e_1_3_2_1_42_1","first-page":"312","volume-title":"Ren et al., \"Vocalprint: exploring a resilient and secure voice authentication via mmwave biometric interrogation,\" in Proceedings of the 18th Conference on Embedded Networked Sensor Systems","author":"Li H.","year":"2020","unstructured":"H. Li, C. Xu, A. S. Rathore, Z. Li, H. Zhang, C. Song, K. Wang, L. Su, F. Lin, K. Ren et al., \"Vocalprint: exploring a resilient and secure voice authentication via mmwave biometric interrogation,\" in Proceedings of the 18th Conference on Embedded Networked Sensor Systems, 2020, pp. 312--325."},{"key":"e_1_3_2_1_43_1","first-page":"6209","volume-title":"Speech and Signal Processing (ICASSP). IEEE","author":"Tao F.","year":"2018","unstructured":"F. Tao, G. Liu, and Q. Zhao, \"An ensemble framework of voice-based emotion recognition system for films and tv programs,\" in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2018, pp. 6209--6213."},{"key":"e_1_3_2_1_44_1","first-page":"2","volume-title":"AAAI","author":"Zhou S.","year":"2021","unstructured":"S. Zhou, J. Jia, Z. Wu, Z. Yang, Y. Wang, W. Chen, F. Meng, S. Huang, J. Shen, and X. Wang, \"Inferring emotion from large-scale internet voice data: A semi-supervised curriculum augmentation based deep learning approach,\" in Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI, 2021, pp. 2--9."},{"key":"e_1_3_2_1_45_1","volume-title":"Listen with intent: Improving speech recognition with audio-to-intent front-end,\" arXiv preprint arXiv:2105.07071","author":"Ray S. N.","year":"2021","unstructured":"S. N. Ray, M. Wu, A. Raju, P. Ghahremani, R. Bilgi, M. Rao, H. Arsikere, A. Rastrow, A. Stolcke, and J. Droppo, \"Listen with intent: Improving speech recognition with audio-to-intent front-end,\" arXiv preprint arXiv:2105.07071, 2021."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3300061.3300125"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41666-020-00090-4"},{"key":"e_1_3_2_1_48_1","unstructured":"B. Schuller F. Friedmann and F. Eyben \"The munich biovoice corpus: Effects of physical exercising heart rate and skin conductance on human speech production \" in Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14) 2014 pp. 1506--1510."},{"key":"e_1_3_2_1_49_1","first-page":"989","volume-title":"Speech and Signal Processing (ICASSP)","author":"Smith J.","year":"2017","unstructured":"J. Smith, A. Tsiartas, E. Shriberg, A. Kathol, A. Willoughby, and M. de Zambotti, \"Analysis and prediction of heart rate using speech features from natural speech,\" in 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017, pp. 989--993."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411843"},{"key":"e_1_3_2_1_51_1","first-page":"1","volume-title":"Monitoring a person's heart rate and respiratory rate on a shared bed using geophones,\" in Proceedings of the 15th ACM Conference on Embedded Network Sensor Systems","author":"Jia Z.","year":"2017","unstructured":"Z. Jia, A. Bonde, S. Li, C. Xu, J. Wang, Y. Zhang, R. E. Howard, and P. Zhang, \"Monitoring a person's heart rate and respiratory rate on a shared bed using geophones,\" in Proceedings of the 15th ACM Conference on Embedded Network Sensor Systems, 2017, pp. 1--14."},{"key":"e_1_3_2_1_52_1","first-page":"37","volume-title":"Vvrrm: Vehicular vibration-based heart rr-interval monitoring system,\" in Proceedings of the 19th International Workshop on Mobile Computing Systems & Applications","author":"Bonde A.","year":"2018","unstructured":"A. Bonde, S. Pan, Z. Jia, Y. Zhang, H. Y. Noh, and P. Zhang, \"Vvrrm: Vehicular vibration-based heart rr-interval monitoring system,\" in Proceedings of the 19th International Workshop on Mobile Computing Systems & Applications, 2018, pp. 37--42."},{"key":"e_1_3_2_1_53_1","first-page":"267","volume-title":"Tracking vital signs during sleep leveraging off-the-shelf wifi,\" in Proceedings of the 16th ACM International Symposium on Mobile Ad Hoc Networking and Computing","author":"Liu J.","year":"2015","unstructured":"J. Liu, Y. Wang, Y. Chen, J. Yang, X. Chen, and J. Cheng, \"Tracking vital signs during sleep leveraging off-the-shelf wifi,\" in Proceedings of the 16th ACM International Symposium on Mobile Ad Hoc Networking and Computing, 2015, pp. 267--276."},{"key":"e_1_3_2_1_54_1","first-page":"211","volume-title":"Monitoring vital signs using millimeter wave,\" in Proceedings of the 17th ACM International Symposium on Mobile Ad Hoc Networking and Computing","author":"Yang Z.","year":"2016","unstructured":"Z. Yang, P. H. Pathak, Y. Zeng, X. Liran, and P. Mohapatra, \"Monitoring vital signs using millimeter wave,\" in Proceedings of the 17th ACM International Symposium on Mobile Ad Hoc Networking and Computing, 2016, pp. 211--220."},{"key":"e_1_3_2_1_55_1","first-page":"1","volume-title":"IEEE","author":"Zhao R.","year":"2018","unstructured":"R. Zhao, D. Wang, Q. Zhang, H. Chen, and A. Huang, \"Crh: A contactless respiration and heartbeat monitoring system with cots rfid tags,\" in 2018 15th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON). IEEE, 2018, pp. 1--9."},{"key":"e_1_3_2_1_56_1","first-page":"315","volume-title":"Cardiac scan: A non-contact and continuous heart-based user authentication system,\" in Proceedings of the 23rd Annual International Conference on Mobile Computing and Networking","author":"Lin F.","year":"2017","unstructured":"F. Lin, C. Song, Y. Zhuang, W. Xu, C. Li, and K. Ren, \"Cardiac scan: A non-contact and continuous heart-based user authentication system,\" in Proceedings of the 23rd Annual International Conference on Mobile Computing and Networking, 2017, pp. 315--328."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3479496"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-016-6243-6"}],"event":{"name":"SenSys '22: The 20th ACM Conference on Embedded Networked Sensor Systems","location":"Boston Massachusetts","acronym":"SenSys '22","sponsor":["SIGMETRICS ACM Special Interest Group on Measurement and Evaluation","SIGCOMM ACM Special Interest Group on Data Communication","SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing","SIGOPS ACM Special Interest Group on Operating Systems","SIGBED ACM Special Interest Group on Embedded Systems","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 20th ACM Conference on Embedded Networked Sensor Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3560905.3568508","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3560905.3568508","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3560905.3568508","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:15Z","timestamp":1750182555000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3560905.3568508"}},"subtitle":["Towards Next Generation Voice-User Interfaces with Cardiac Sensing Functions"],"short-title":[],"issued":{"date-parts":[[2022,11,6]]},"references-count":58,"alternative-id":["10.1145\/3560905.3568508","10.1145\/3560905"],"URL":"https:\/\/doi.org\/10.1145\/3560905.3568508","relation":{},"subject":[],"published":{"date-parts":[[2022,11,6]]},"assertion":[{"value":"2023-01-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}