{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T04:01:46Z","timestamp":1748491306168,"version":"3.41.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icasspw65056.2025.11011178","type":"proceedings-article","created":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T17:05:14Z","timestamp":1748365514000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Prosody Disentanglement with Self-Supervised Speech Representation for Detecting Depression"],"prefix":"10.1109","author":[{"given":"Bubai","family":"Maji","sequence":"first","affiliation":[{"name":"IIT Kharagpur,Rekhi Centre of Excellence for the Science of Happiness,India"}]},{"given":"Rajlakshmi","family":"Guha","sequence":"additional","affiliation":[{"name":"IIT Kharagpur,Rekhi Centre of Excellence for the Science of Happiness,India"}]},{"given":"Aurobinda","family":"Routray","sequence":"additional","affiliation":[{"name":"IIT Kharagpur,Department of Electrical Engineering,India"}]},{"given":"Shazia","family":"Nasreen","sequence":"additional","affiliation":[{"name":"IIT Kharagpur,Rekhi Centre of Excellence for the Science of Happiness,India"}]},{"given":"Debabrata","family":"Majumdar","sequence":"additional","affiliation":[{"name":"IIT Kharagpur,B C Roy Technology Hospital,India"}]}],"member":"263","reference":[{"volume-title":"Non-verbal communication in depression.","year":"2007","author":"Ellgring","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.7407"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2021.713823"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2018.05.007"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3154332"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2522"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-296"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2024.08.002"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/s21041249"},{"key":"ref10","first-page":"21","article-title":"Vocal tract length perturbation (vtlp) improves speech recognition","volume-title":"Proc. ICML workshop on deep learning for audio, speech and language","volume":"117","author":"Jaitly"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054579"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746307"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096105"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref17","first-page":"12 449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10627629"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1122"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10626129"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1737"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2237"},{"key":"ref23","first-page":"2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Kenton"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1002\/9781118706664"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593571"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2650"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128209"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC40787.2023.10341118"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1176\/appi.ajp.2009.09020279"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988267"}],"event":{"name":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","start":{"date-parts":[[2025,4,6]]},"location":"Hyderabad, India","end":{"date-parts":[[2025,4,11]]}},"container-title":["2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11010992\/11010997\/11011178.pdf?arnumber=11011178","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T04:53:24Z","timestamp":1748408004000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11011178\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icasspw65056.2025.11011178","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}