{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T06:44:57Z","timestamp":1764225897774,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,25]],"date-time":"2023-10-25T00:00:00Z","timestamp":1698192000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,25]],"date-time":"2023-10-25T00:00:00Z","timestamp":1698192000000},"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":[[2023,10,25]]},"DOI":"10.1109\/sped59241.2023.10314932","type":"proceedings-article","created":{"date-parts":[[2023,11,15]],"date-time":"2023-11-15T18:50:55Z","timestamp":1700074255000},"page":"100-104","source":"Crossref","is-referenced-by-count":3,"title":["An analysis of large speech models-based representations for speech emotion recognition"],"prefix":"10.1109","author":[{"given":"Adrian Bogdan","family":"St\u00e2nea","sequence":"first","affiliation":[{"name":"Technical University of Cluj-Napoca,Communications Department,Romania"}]},{"given":"Vlad","family":"Strile\u021bchi","sequence":"additional","affiliation":[{"name":"Technical University of Cluj-Napoca,Communications Department,Romania"}]},{"given":"Cosmin","family":"Strile\u021bchi","sequence":"additional","affiliation":[{"name":"Technical University of Cluj-Napoca,Communications Department,Romania"}]},{"given":"Adriana","family":"Stan","sequence":"additional","affiliation":[{"name":"Technical University of Cluj-Napoca,Communications Department,Romania"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2010.09.020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1353"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.07.005"},{"key":"ref4","first-page":"2305","article-title":"Ctl-mtnet: A novel capsnet and transfer learning-based mixed task net for single-corpus and cross-corpus speech emotion recognition","volume-title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI 2022, Vienna, Austria, 23-29 July 2022","author":"Wen"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096370"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-703"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"article-title":"EMOVO Corpus: an Italian Emotional Speech Database","volume-title":"International Conference on Language Resources and Evaluation","author":"Costantini","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-446"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-61520-919-4"},{"key":"ref13","article-title":"A toolbox for construction and analysis of speech datasets","volume-title":"NeurIPS Datasets and Benchmarks","author":"Bakhturina","year":"2021"},{"article-title":"Speakernet: 1d depth-wise separable convolutional network for text-independent speaker recognition and verification","year":"2020","author":"Koluguri","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746806"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2020-2650","article-title":"ECAPA-TDNN: Emphasized channel attention, propagation and aggregation in TDNN based speaker verification","volume-title":"Interspeech 2020","author":"Desplanques","year":"2020"},{"key":"ref17","first-page":"12 449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Baevski","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053176"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICEIC57457.2023.10049941"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1705"},{"issue":"21","key":"ref22","article-title":"Residual information in deep speaker embedding architectures","volume-title":"Mathematics","volume":"10","author":"Stan","year":"2022"}],"event":{"name":"2023 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","start":{"date-parts":[[2023,10,25]]},"location":"Bucharest, Romania","end":{"date-parts":[[2023,10,27]]}},"container-title":["2023 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10314856\/10314866\/10314932.pdf?arnumber=10314932","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T17:24:11Z","timestamp":1709400251000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10314932\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,25]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/sped59241.2023.10314932","relation":{},"subject":[],"published":{"date-parts":[[2023,10,25]]}}}