{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T12:29:40Z","timestamp":1773059380625,"version":"3.50.1"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446997","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11631-11635","source":"Crossref","is-referenced-by-count":14,"title":["Improving Domain Generalization in Speech Emotion Recognition with Whisper"],"prefix":"10.1109","author":[{"given":"Erik","family":"Goron","sequence":"first","affiliation":[{"name":"Maaind Technologies"}]},{"given":"Lena","family":"Asai","sequence":"additional","affiliation":[{"name":"Maaind Technologies"}]},{"given":"Elias","family":"Rut","sequence":"additional","affiliation":[{"name":"Maaind Technologies"}]},{"given":"Martin","family":"Dinov","sequence":"additional","affiliation":[{"name":"Maaind Technologies"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/79.911197"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0706743719828977"},{"key":"ref3","first-page":"22","article-title":"Emotion in speech: Recognition and application to call centers","volume-title":"Proceedings of artificial neural networks in engineering","volume":"710","author":"Petrushin"},{"key":"ref4","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref8","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-703"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/slt48900.2021.9383456"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.20944\/preprints202008.0645.v1","article-title":"Recognizing more emotions with less data using self-supervised transfer learning","author":"Boigne","year":"2020"},{"key":"ref12","article-title":"Using large pre-trained models with cross-modal attention for multi-modal emotion recognition","author":"Freshworks","year":"2021"},{"key":"ref13","article-title":"A fine-tuned wav2vec 2.0\/hubert benchmark for speech emotion recognition, speaker verification and spoken language understanding","author":"Wang","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095036"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2024.3369726"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095193"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2916092"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-111"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3167013"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2020.2972926"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747129"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003838"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-736"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1356"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383534"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687987"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3263585"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/IberSPEECH.2022-16"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747417"},{"key":"ref30","article-title":"In search of lost domain generalization","author":"Gulrajani","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3204949.3208121"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-446"},{"key":"ref35","article-title":"Audio,Speech and Vision Processing Lab Emotional Sound database (ASVP-ESD)","author":"Landry Dejoli","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"},{"key":"ref37","article-title":"Domain generalization by marginal transfer learning","author":"Blanchard","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref39","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446997.pdf?arnumber=10446997","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:29:35Z","timestamp":1722572975000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446997\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446997","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}