{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T15:24:36Z","timestamp":1783178676802,"version":"3.54.6"},"reference-count":26,"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\/icassp48485.2024.10448316","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11026-11030","source":"Crossref","is-referenced-by-count":20,"title":["Large Language Model-Based Emotional Speech Annotation Using Context and Acoustic Feature for Speech Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Jennifer","family":"Santoso","sequence":"first","affiliation":[{"name":"RevComm, Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kenkichi","family":"Ishizuka","sequence":"additional","affiliation":[{"name":"RevComm, Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taiichi","family":"Hashimoto","sequence":"additional","affiliation":[{"name":"RevComm, Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.117"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00407"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747095"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095611"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-411"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-555"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054441"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1090"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414286"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-756"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747870"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-57"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414880"},{"key":"ref15","author":"Zhu","year":"2023","journal-title":"Can chatgpt reproduce human-generated labels? a study of social computing tasks"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3543873.3587368"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1832"},{"key":"ref18","first-page":"242","article-title":"Evaluating large-language models for dimensional music emotion prediction from social media discourse","volume-title":"Proceedings of the 5th International Conference on Natural Language and Speech Processing (ICNLSP 2022)","author":"Donnelly"},{"key":"ref19","author":"Dhamyal","year":"2022","journal-title":"Describing emotions with acoustic property prompts for speech emotion recognition"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2929050"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3273577"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1544"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.25080\/majora-7b98e3ed-003"},{"key":"ref25","author":"Devlin","year":"2018","journal-title":"Bert: Pretraining of deep bidirectional transformers for language understanding"},{"key":"ref26","author":"Chernykh","year":"2017","journal-title":"Emotion recognition from speech with recurrent neural networks"}],"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\/10448316.pdf?arnumber=10448316","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:52:11Z","timestamp":1722660731000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448316\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448316","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}