{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:16:52Z","timestamp":1764400612980,"version":"3.46.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11248989","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"747-752","source":"Crossref","is-referenced-by-count":0,"title":["PUNSER: Large-Scale Pre-Trained and Unified Model for Practical Speech Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Yu","family":"Hayashizaki","sequence":"first","affiliation":[{"name":"Tohoku University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takashi","family":"Nose","sequence":"additional","affiliation":[{"name":"Tohoku University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sumiharu","family":"Kobayashi","sequence":"additional","affiliation":[{"name":"Tohoku University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satoru","family":"Fukayama","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST),Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akinori","family":"Ito","sequence":"additional","affiliation":[{"name":"Tohoku University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"119","article-title":"Speech emotion recognition for call centers using selfsupervised models: A complete pipeline for industrial applications","volume-title":"Proc. ICNLSP","author":"Mart\u00edn-Do\u00f1as","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-398"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446997"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10581"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448316"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.570"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.931"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2594"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1852"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096700"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/app15020623"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3610661.3616190"},{"key":"ref16","first-page":"1","article-title":"Robust speech emotion recognition using recent selfsupervised learning with data augmentation","volume-title":"2025 IEEE 12th Global Conference on Consumer Electronics (GCCE)","author":"Hayashizaki","year":"2025"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"issue":"5","key":"ref19","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 Journal"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1227"},{"journal-title":"ESCorpus-PE: A speech emotional dataset in spanish with peruvian accent","year":"2021","author":"Parari","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3204949.3208121"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01855-9"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2016.7918977"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2515617"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.08.002"},{"volume-title":"Surrey audio-visual expressed emotion (savee) database","year":"2014","author":"Jackson","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-446"},{"journal-title":"Testing speech emotion recognition machine learning models","year":"2023","author":"Derington","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096966"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095193"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11248989.pdf?arnumber=11248989","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:15:26Z","timestamp":1764400526000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11248989\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11248989","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}