{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T17:35:54Z","timestamp":1783704954216,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China","award":["61901265"],"award-info":[{"award-number":["61901265"]}]},{"name":"Shanghai Pujiang Program","award":["19PJ1406300"],"award-info":[{"award-number":["19PJ1406300"]}]},{"name":"State Key Laboratory of Media Convergence Production Technology and Systems Project","award":["SKLMCPTS2020003"],"award-info":[{"award-number":["SKLMCPTS2020003"]}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3479236","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T08:03:42Z","timestamp":1634544222000},"page":"135-143","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":53,"title":["DEPA"],"prefix":"10.1145","author":[{"given":"Pingyue","family":"Zhang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengyue","family":"Wu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heinrich","family":"Dinkel","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Yu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2522"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157196"},{"key":"e_1_3_2_2_3_1","volume-title":"International conference on machine learning. PMLR, 1597--1607","author":"Chen Ting","year":"2020"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853741"},{"key":"e_1_3_2_2_5_1","volume-title":"COVAREP-A collaborative voice analysis repository for speech technologies. In 2014 ieee international conference on acoustics, speech and signal processing (icassp)","author":"Degottex Gilles"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/2615731.2617415"},{"key":"e_1_3_2_2_7_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018"},{"key":"e_1_3_2_2_8_1","volume-title":"Speech and Computer,","author":"Egas L\u00f3pez Jos\u00e9 Vicente"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/1895550.1895693"},{"key":"e_1_3_2_2_10_1","volume-title":"Self-supervised co-training for video representation learning. arXiv preprint arXiv:2010.09709","author":"Han Tengda","year":"2020"},{"key":"e_1_3_2_2_11_1","volume-title":"Measuring Depression Symptom Severity from Spoken Language and 3D Facial Expressions. arXiv preprint arXiv:1811.08592","author":"Haque Albert","year":"2018"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1093\/geroni\/igz038.1665"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988267"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"crossref","unstructured":"Jeffrey Pennington Richard Socher and Christopher D Manning. 2014. GloVe: Global Vectors for Word Representation. In Empirical Methods in Natural Language Processing (EMNLP). 1532--1543. http:\/\/www.aclweb.org\/anthology\/D14--1162  Jeffrey Pennington Richard Socher and Christopher D Manning. 2014. GloVe: Global Vectors for Word Representation. In Empirical Methods in Natural Language Processing (EMNLP). 1532--1543. http:\/\/www.aclweb.org\/anthology\/D14--1162","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"e_1_3_2_2_18_1","volume-title":"IEEE 2011 workshop on automatic speech recognition and understanding. IEEE Signal Processing Society.","author":"Povey Daniel","year":"2011"},{"key":"e_1_3_2_2_19_1","volume-title":"2019 a. Clinical Depression and Affect Recognition with EmoAudioNet. CoRR","author":"Rejaibi Emna","year":"2019"},{"key":"e_1_3_2_2_20_1","volume-title":"2019 b. MFCC-based Recurrent Neural Network for Automatic Clinical Depression Recognition and Assessment from Speech. arXiv preprint arXiv:1909.07208","author":"Rejaibi Emna","year":"2019"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682467"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3214284"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/HealthCom.2018.8531119"},{"key":"e_1_3_2_2_25_1","volume-title":"F\u00e9lix de Chaumont Quitry, and Dominik Roblek","author":"Tagliasacchi Marco","year":"2019"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988258"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988263"},{"key":"e_1_3_2_2_28_1","volume-title":"The Sound of Pixels. CoRR","author":"Zhao Hang","year":"2018"}],"event":{"name":"MM '21: ACM Multimedia Conference","location":"Virtual Event China","acronym":"MM '21","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3479236","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3479236","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:49Z","timestamp":1750193329000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3479236"}},"subtitle":["Self-Supervised Audio Embedding for Depression Detection"],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":28,"alternative-id":["10.1145\/3474085.3479236","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3479236","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]},"assertion":[{"value":"2021-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}