{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T17:12:23Z","timestamp":1780420343084,"version":"3.54.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096552","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["Evaluating Variants of wav2vec 2.0 on Affective Vocal Burst Tasks"],"prefix":"10.1109","author":[{"given":"Bagus Tris","family":"Atmaja","sequence":"first","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology,Tsukuba,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akira","family":"Sasou","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology,Tsukuba,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551591"},{"key":"ref12","article-title":"The ICML 2022 Expressive Vocalizations Workshop and Competition: Recognizing, Generating, and Personalizing Vocal Bursts","author":"baird","year":"2022","journal-title":"Proc ICML Expressive Vocalizations Work Compet"},{"key":"ref34","article-title":"End2You-The Imperial Toolkit for Multimodal Profiling by End-to-End Learning","author":"tzirakis","year":"2018"},{"key":"ref15","article-title":"Dawn of the transformer era in speech emotion recognition: closing the valence gap","author":"wagner","year":"2022"},{"key":"ref14","article-title":"The ACII 2022 Affective Vocal Bursts Workshop & Competition: Understanding a critically understudied modality of emotional expression","author":"baird","year":"2022","journal-title":"10th Int Conf Affect Comput Intell Interact Work Demos (ACIIW)"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"12004","DOI":"10.1088\/1742-6596\/1896\/1\/012004","article-title":"Evaluation of errorand correlation-based loss functions for multitask learning dimensional speech emotion recognition","volume":"1896","author":"atmaja","year":"2021","journal-title":"J Phys Conf Ser"},{"key":"ref30","article-title":"Decoupled Weight Decay Regularization","author":"loshchilov","year":"2019","journal-title":"7th Int Conf Learn Represent ICLR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(02)00084-5"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1037\/amp0000399"},{"key":"ref32","article-title":"Switchboard-1 Release 2 LDC97S62","author":"godfrey","year":"1993","journal-title":"Linguistic Data Consortium (LDC)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1111\/j.0963-7214.2004.00303.x"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/17470211003721642"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACIIW57231.2022.10085991"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2020.11.003"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9980310"},{"key":"ref24","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref26","first-page":"750","article-title":"A Multilingual Framework Based on Pre-training Model for Speech Emotion Recognition","author":"zhang","year":"2021","journal-title":"APSIPA Annual Summit and Conference"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-703"},{"key":"ref20","article-title":"The Hume Vocal Burst Competition Dataset (H-VB) — Raw Data [ExVo: updated 02.28.22] [Data set]","author":"cowen","year":"2022","journal-title":"Zenodo"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-56"},{"key":"ref28","article-title":"Model for Dimensional Speech Emotion Recognition based on Wav2vec 2.0 (1.1.0)","author":"wagner","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-236"},{"key":"ref29","article-title":"Layer Normalization","author":"ba","year":"2015"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2388676.2388776"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-88431-0"},{"key":"ref4","first-page":"39","article-title":"Recognizing emotions in dialogues with disfluencies and non-verbal vocalisations","author":"tian","year":"2015","journal-title":"Proc ofthe 4th Interdiscip Work Laugh Other Non-verbal Vocalisations Speech"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0926-6410(99)00060-9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846319"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2015.7344645"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096552.pdf?arnumber=10096552","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T18:57:07Z","timestamp":1699901827000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096552\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096552","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}