{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T17:20:09Z","timestamp":1778606409157,"version":"3.51.4"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,18]],"date-time":"2022-10-18T00:00:00Z","timestamp":1666051200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,18]],"date-time":"2022-10-18T00:00:00Z","timestamp":1666051200000},"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":[[2022,10,18]]},"DOI":"10.1109\/aciiw57231.2022.10085991","type":"proceedings-article","created":{"date-parts":[[2023,4,5]],"date-time":"2023-04-05T17:23:35Z","timestamp":1680715415000},"page":"1-6","source":"Crossref","is-referenced-by-count":7,"title":["Jointly Predicting Emotion, Age, and Country Using Pre-Trained Acoustic Embedding"],"prefix":"10.1109","author":[{"given":"Bagus Tris","family":"Atmaja","sequence":"first","affiliation":[{"name":"AIST,Tsukuba,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Zanjabila","sequence":"additional","affiliation":[{"name":"ITS,Surabaya,Indonesia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akira","family":"Sasou","sequence":"additional","affiliation":[{"name":"AIST,Tsukuba,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3021015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/aciiw57231.2022.10086002"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1037\/amp0000399"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1037\/\/0033-2909.99.2.143"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551591"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.06.002"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/BDS\/HPSC\/IDS18.2018.00018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1494"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683046"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-736"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1896\/1\/012004"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1700"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1852"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3189481"},{"key":"ref15","author":"Wagner","year":"2022","journal-title":"Model for Dimensional Speech Emotion Recognition based on Wav2vec 2.0 (1.1.0)"},{"key":"ref16","author":"Wagner","year":"2022","journal-title":"Dawn of the transformer era in speech emotion recognition: closing the valence gap"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-236"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref19","author":"Ba","year":"2015","journal-title":"Layer Normalization"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054709"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60276-5_30"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.03.002"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01261-8_1","volume-title":"Group Normalization","author":"Wu","year":"2018"},{"key":"ref24","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"32nd Int. Conf. Mach. Learn. ICML 2015","volume":"1","author":"Ioffe","year":"2015"},{"key":"ref25","volume-title":"librosa\/librosa: 0.7.2","author":"McFee","year":"2020"},{"issue":"Figure 1","key":"ref26","first-page":"1","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"2020-Decem","author":"Baevski","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref27","author":"Tzirakis","year":"2018","journal-title":"End2You-The Imperial Toolkit for Multimodal Profiling by End-to-End Learning"}],"event":{"name":"2022 10th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW)","location":"Nara, Japan","start":{"date-parts":[[2022,10,17]]},"end":{"date-parts":[[2022,10,21]]}},"container-title":["2022 10th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10085961\/10085990\/10085991.pdf?arnumber=10085991","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T06:41:31Z","timestamp":1710398491000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10085991\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,18]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/aciiw57231.2022.10085991","relation":{},"subject":[],"published":{"date-parts":[[2022,10,18]]}}}