{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T07:00:19Z","timestamp":1763535619684,"version":"3.28.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683498","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"6525-6529","source":"Crossref","is-referenced-by-count":29,"title":["Learning Voice Source Related Information for Depression Detection"],"prefix":"10.1109","author":[{"given":"S. Pavankumar","family":"Dubagunta","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bogdan","family":"Vlasenko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mathew","family":"Magimai.-Doss","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"End-to-end acoustic modeling using convolutional neural networks for automatic speech recognition","author":"palaz","year":"2016","journal-title":"Tech Rep Idiap-RR-18-2016"},{"article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","year":"2015","author":"abadi","key":"ref38"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"44","DOI":"10.21437\/Interspeech.2013-10","article-title":"Detection of glottal opening instants using hilbert envelope","author":"ramesh","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s12046-011-0046-0"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2004526"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"116","DOI":"10.21437\/Interspeech.2009-27","article-title":"Complex cepstrum-based decomposition of speech for glottal source estimation","author":"drugman","year":"2009","journal-title":"Proc INTERSPEECH"},{"article-title":"Keras","year":"2015","author":"chollet","key":"ref37"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2008.06.026"},{"key":"ref34","first-page":"3123","article-title":"The distress analysis interview corpus of human and computer interviews","author":"gratch","year":"2014","journal-title":"Proc of LREC ELRA"},{"key":"ref10","first-page":"847","article-title":"Investigating voice quality as a speaker-independent indicator of depression and PTSD","author":"scherer","year":"2013","journal-title":"Proc In-terspeech"},{"key":"ref40","article-title":"Gradient-based spectral visualization of CNNs using raw waveforms","author":"muckenhirn","year":"2018","journal-title":"Tech Rep Idiap-RR-11-2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1251"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-867"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-120"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2018.05.007"},{"key":"ref15","first-page":"35","article-title":"De-pAudioNet: An Efficient Deep Model for Audio Based Depression Classification","author":"ma","year":"2016","journal-title":"Proc AVEC International Workshop"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1176\/ajp.154.1.4","article-title":"Psychomotor symptoms of depression","volume":"154","author":"sobin","year":"1997","journal-title":"American Journal of Psychiatry"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/S0165-0327(99)00068-3"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2004.827544"},{"key":"ref19","first-page":"1059","article-title":"Vocal-source biomarkers for depression: A link to psychomotor activity","author":"quatieri","year":"2012","journal-title":"Proc Inter-speech"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1975.9792"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2522"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2014.03.003"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2017.2676878"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1080\/0269920031000086248"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAU.1972.1162410"},{"key":"ref5","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":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1566"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1399"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988258"},{"key":"ref9","first-page":"1248","article-title":"Automatic modelling of depressed speech: Relevant features and relevance of gender","author":"h\u00f6nig","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2015.03.004"},{"key":"ref20","first-page":"1766","article-title":"Estimating phoneme class conditional probabilities from raw speech signal using convolutional neural networks","author":"palaz","year":"2013","journal-title":"Proc Inter-speech"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1696"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462165"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2360"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1240"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163267"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1281"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, United Kingdom","end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683498.pdf?arnumber=8683498","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,17]],"date-time":"2024-07-17T00:55:25Z","timestamp":1721177725000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683498\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683498","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}