{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T10:19:07Z","timestamp":1778408347118,"version":"3.51.4"},"reference-count":37,"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\/icassp49660.2025.10890672","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":7,"title":["voc2vec: A Foundation Model for Non-Verbal Vocalization"],"prefix":"10.1109","author":[{"given":"Alkis","family":"Koudounas","sequence":"first","affiliation":[{"name":"Politecnico di Torino,Turin,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Moreno","family":"La Quatra","sequence":"additional","affiliation":[{"name":"Kore University of Enna,Enna,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sabato Marco","family":"Siniscalchi","sequence":"additional","affiliation":[{"name":"Università Degli Studi di Palermo,Palermo,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elena","family":"Baralis","sequence":"additional","affiliation":[{"name":"Politecnico di Torino,Turin,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2201476"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095294"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448130"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2016.00506"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/1529100619850176"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462677"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3243012"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1159"},{"key":"ref11","first-page":"4171","article-title":"BERT: Pretraining of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Devlin"},{"key":"ref12","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Brown","year":"2020"},{"key":"ref13","first-page":"12449","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1980"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP61759.2024.10743615"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1122"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3551876.3554801"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref22","article-title":"Exploring the effectiveness of self-supervised learning and classifier chains in emotion recognition of nonverbal vocalizations","author":"Xin","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.931"},{"key":"ref25","first-page":"486","article-title":"Freesound datasets: a platform for the creation of open audio datasets","volume-title":"Proceedings of the 18th ISMIR Conference; 2017 oct 23-27; Suzhou, China. [Canada]: International Society for Music Information Retrieval; 2017","author":"Fonseca"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2017.8273615"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1049\/sil2.12233"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02405-7"},{"key":"ref29","article-title":"Automatic identification of emotional cues in chinese opera singing","author":"Black","year":"2014","journal-title":"ICMPC, Seoul, South Korea"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702387"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746828"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10625960"},{"key":"ref34","first-page":"1793","article-title":"Asvp-esd: A dataset and its benchmark for emotion recognition using both speech and non-speech utterances","volume":"8","author":"Landry","year":"2020","journal-title":"Global Scientific Journals"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-201"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1037\/emo0001048"},{"key":"ref37","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"International Conference on Machine Learning","author":"Baevski"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890672.pdf?arnumber=10890672","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:14Z","timestamp":1774416194000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890672\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890672","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}