{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T00:11:43Z","timestamp":1783469503379,"version":"3.55.0"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61876112"],"award-info":[{"award-number":["61876112"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61601311"],"award-info":[{"award-number":["61601311"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Natural Science Foundation of Beijing","doi-asserted-by":"publisher","award":["L201022"],"award-info":[{"award-number":["L201022"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tcds.2023.3273614","type":"journal-article","created":{"date-parts":[[2023,5,8]],"date-time":"2023-05-08T19:04:58Z","timestamp":1683572698000},"page":"308-318","source":"Crossref","is-referenced-by-count":61,"title":["Spatial\u2013Temporal Feature Network for Speech-Based Depression Recognition"],"prefix":"10.1109","volume":"16","author":[{"given":"Zhuojin","family":"Han","sequence":"first","affiliation":[{"name":"College of Information Engineering and the Beijing Key Laboratory of Electronic System Reliability Technology, Capital Normal University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3135-0348","authenticated-orcid":false,"given":"Yuanyuan","family":"Shang","sequence":"additional","affiliation":[{"name":"College of Information Engineering and the Beijing Key Laboratory of Electronic System Reliability Technology, Capital Normal University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuhong","family":"Shao","sequence":"additional","affiliation":[{"name":"College of Information Engineering and the Beijing Engineering Research Center of Highly Reliable Embedded System, Capital Normal University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingyi","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Mathematical Sciences and the Beijing Key Laboratory of Electronic System Reliability Technology, Capital Normal University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9583-0055","authenticated-orcid":false,"given":"Guodong","family":"Guo","sequence":"additional","affiliation":[{"name":"Lane Department of Computer Science and Electrical Engineering, West Virginia University, Morgantown, WV, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tie","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Information Engineering and the Beijing Engineering Research Center of Highly Reliable Embedded System, Capital Normal University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Ding","sequence":"additional","affiliation":[{"name":"College of Information Engineering and the Beijing Engineering Research Center of Highly Reliable Embedded System, Capital Normal University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Psychiatry, Zhenjiang Mental Health Center, Zhenjiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(16)31678-6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nrdp.2016.65"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2018.2828819"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2650899"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2021.3139651"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.10.015"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3072579"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1111\/j.1749-6632.1980.tb21255.x"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2015.03.004"},{"key":"ref10","first-page":"89","article-title":"Decision tree based depression classification from audio video and language information","volume-title":"Proc. 6th Int. Workshop Audio Vis. Emotion Challenge","author":"Le"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2015.7344581"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2019.12.228"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.02.019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2017.8273643"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2970496"},{"key":"ref16","article-title":"Significance of speaker embeddings and temporal context for depression detection","author":"Dumpala","year":"2021","journal-title":"arXiv:2107.13969"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988267"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CAC.2018.8623055"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2512530.2512533"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988266"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/O-COCOSDA50338.2020.9295039"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2018.00326"},{"key":"ref23","article-title":"Multimodal depression detection: An investigation of features and fusion techniques for automated systems","author":"Morales","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479236"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2018.05.007"},{"key":"ref26","article-title":"Raw audio for depression detection can be more robust against gender imbalance than melspectrogram features","author":"Bailey","year":"2020","journal-title":"arXiv:2010.15120"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2512530.2512531"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2661806.2661818"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/iSAI-NLP48611.2019.9045499"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICECDS.2017.8390102"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639227"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-18305-9_47"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSP49548.2020.9163547"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2217"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref37","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"Baevski","year":"2019","journal-title":"arXiv:1910.05453"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-997"},{"key":"ref39","first-page":"3123","article-title":"The distress analysis interview corpus of human and computer interviews","volume-title":"Proc. 9th Int. Conf. Lang. Resour. Eval. (LREC)","author":"Gratch"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133953"},{"key":"ref41","first-page":"1061","article-title":"SimSensei kiosk: A virtual human interviewer for healthcare decision support","volume-title":"Proc. Int. Conf. Auton. Agents Multi-Agent Syst.","author":"DeVault"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3347320.3357688"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-140"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1710.09412"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414018"},{"key":"ref47","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"arXiv:2006.11477"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3347320.3357694"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3347320.3357697"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3347320.3357693"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988258"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2019.2925204"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054323"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.103107"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2522"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133951"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683027"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68790-8_1"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/10419120\/10120969.pdf?arnumber=10120969","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,6]],"date-time":"2024-02-06T20:25:18Z","timestamp":1707251118000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10120969\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":58,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2023.3273614","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}