{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:37:25Z","timestamp":1783557445374,"version":"3.55.0"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2020,2,1]],"date-time":"2020-02-01T00:00:00Z","timestamp":1580515200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,2,1]],"date-time":"2020-02-01T00:00:00Z","timestamp":1580515200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,2,1]],"date-time":"2020-02-01T00:00:00Z","timestamp":1580515200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"crossref","award":["61425017"],"award-info":[{"award-number":["61425017"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Key Program of the National Natural Science Foundation of China","award":["61831022"],"award-info":[{"award-number":["61831022"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702370"],"award-info":[{"award-number":["61702370"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Projects Program of the National Laboratory of Pattern Recognition"},{"name":"Key Program of the Natural Science Foundation of Tianjin","award":["18JCZDJC36300"],"award-info":[{"award-number":["18JCZDJC36300"]}]},{"name":"European Unions Horizon 2020 research and innovation programme","award":["115902"],"award-info":[{"award-number":["115902"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2020,2]]},"DOI":"10.1109\/jstsp.2019.2955012","type":"journal-article","created":{"date-parts":[[2019,11,22]],"date-time":"2019-11-22T21:18:36Z","timestamp":1574457516000},"page":"423-434","source":"Crossref","is-referenced-by-count":91,"title":["Automatic Assessment of Depression From Speech via a Hierarchical Attention Transfer Network and Attention Autoencoders"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8719-6389","authenticated-orcid":false,"given":"Ziping","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6618-5325","authenticated-orcid":false,"given":"Zhongtian","family":"Bao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8487-0561","authenticated-orcid":false,"given":"Zixing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3196-8690","authenticated-orcid":false,"given":"Jun","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1178-917X","authenticated-orcid":false,"given":"Nicholas","family":"Cummins","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1617-0920","authenticated-orcid":false,"given":"Haishuai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9344-6428","authenticated-orcid":false,"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6478-8699","authenticated-orcid":false,"given":"Bjorn","family":"Schuller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988261"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2015.09.003"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639227"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2012.38"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.04.001"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-59758-4_23"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2766145"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2661806.2661809"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988263"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2661806.2661818"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref62","first-page":"2837","article-title":"Online and linear-time attention by enforcing monotonic alignments","author":"raffel","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref61","first-page":"16","article-title":"Monotonic chunkwise attention","author":"chiu","year":"0","journal-title":"Proc Intl Conf on Learning Representations"},{"key":"ref63","first-page":"431","article-title":"Local monotonic attention mechanism for end-to-end speech and language processing","author":"tjandra","year":"0","journal-title":"Proc 8th Int Joint Conf Natural Lang Process"},{"key":"ref28","first-page":"4978","article-title":"An unsupervised model with attention autoencoders for question retrieval","author":"zhang","year":"0","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref64","first-page":"3123","article-title":"The distress analysis interview corpus of human and computer interviews","author":"gratch","year":"0","journal-title":"Proc Int Conf Lang Resources Eval"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1107"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2008.06.026"},{"key":"ref66","year":"1994","journal-title":"DSM-IV Diagnostic and Statistical Manual of Mental Disorders"},{"key":"ref29","first-page":"2997","article-title":"An investigation of depressed speech detection: Features and normalization","author":"cummins","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3267935.3267948"},{"key":"ref68","article-title":"The CMU pronouncing dictionary","author":"lenzo","year":"2007"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2512530.2512533"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2015.03.004"},{"key":"ref20","first-page":"41","article-title":"The increasing impact of deep learning on speech analysis for health: Challenges and opportunities","volume":"151","author":"cummins","year":"2018","journal-title":"Methods Special Issue Trans Data Analytics Health Inform"},{"key":"ref22","first-page":"625","article-title":"Why does unsupervised pre-training help deep learning","volume":"11","author":"erhan","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2699358"},{"key":"ref24","first-page":"37","article-title":"Autoencoders, unsupervised learning, and deep architectures","author":"baldi","year":"0","journal-title":"Proc ICML Workshop Unsupervised Transfer Learn"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2759338"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.277"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.06.013"},{"key":"ref50","first-page":"15","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1477"},{"key":"ref59","first-page":"13","article-title":"Fitnets: Hints for thin deep nets","author":"romero","year":"0","journal-title":"Proc 3th International Conference for Learning Representations"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2672753"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2324759"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2013.90"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1568"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1561\/2200000006"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01424-7_27"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2018.2870398"},{"key":"ref11","first-page":"597","article-title":"Abandoning emotion classes – Towards continuous emotion recognition with modelling of long-range dependencies","author":"w\u00f6llmer","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1109\/TAFFC.2015.2440264","article-title":"Self-reported symptoms of depression and PTSD are associated with reduced vowel space in screening interviews","volume":"7","author":"scherer","year":"2016","journal-title":"IEEE Trans Affect Comput"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952552"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1174"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1207"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683801"},{"key":"ref16","first-page":"13","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"zagoruyko","year":"0","journal-title":"Proc Intl Conf on Learning Representations"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123432"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123292"},{"key":"ref19","first-page":"2760","article-title":"Paraphrasing complex network: Network compression via factor transfer","author":"kim","year":"0","journal-title":"Proc 32nd Annu Conf Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988258"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2661806.2661807"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3266302.3266316"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133953"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133948"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2018.05.007"},{"key":"ref49","first-page":"2773","article-title":"Grammar as a foreign language","author":"vinyals","year":"0","journal-title":"Proc 29th Conf Neural Inf Process Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133950"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2017.8273599"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764438"},{"key":"ref48","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"0","journal-title":"Proc 29th Conf Neural Inf Process Syst"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-448"},{"key":"ref42","first-page":"960","article-title":"Covarepa collaborative voice analysis repository for speech technologies","author":"degottex","year":"0","journal-title":"Proc 39th IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502224"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2019.01.006"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988267"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/9059048\/08910358.pdf?arnumber=8910358","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:05:57Z","timestamp":1651079157000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8910358\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2]]},"references-count":68,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2019.2955012","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,2]]}}}