{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:06:55Z","timestamp":1776888415510,"version":"3.51.2"},"reference-count":30,"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\/icassp48485.2024.10448130","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"12116-12120","source":"Crossref","is-referenced-by-count":24,"title":["Foundation Model Assisted Automatic Speech Emotion Recognition: Transcribing, Annotating, and Augmenting"],"prefix":"10.1109","author":[{"given":"Tiantian","family":"Feng","sequence":"first","affiliation":[{"name":"University of Southern California,Signal Analysis and Interpretation Laboratory,Los Angeles,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shrikanth","family":"Narayanan","sequence":"additional","affiliation":[{"name":"University of Southern California,Signal Analysis and Interpretation Laboratory,Los Angeles,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"12 449","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":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref4","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5494979"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000084"},{"key":"ref8","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"ref9","article-title":"Gpt-4 technical report","volume-title":"ArXiv","volume":"abs\/2303.08774","year":"2023"},{"key":"ref10","article-title":"Scaling speech technology to 1,000+ languages","author":"Pratap","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746289"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639583"},{"key":"ref13","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref14","article-title":"Falcon llm"},{"key":"ref15","article-title":"Scaling instruction-finetuned language models","author":"Chung","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1832"},{"key":"ref17","article-title":"Can large language models aid in annotating speech emotional data? uncovering new frontiers","author":"Latif","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.lindif.2023.102274"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747265"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACII52823.2021.9597433"},{"key":"ref21","article-title":"Exploring wav2vec 2.0 fine-tuning for improved speech emotion recognition","author":"Chen","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-703"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-78665-0_6085"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2515617"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref27","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414286"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2078"}],"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\/10448130.pdf?arnumber=10448130","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T06:49:29Z","timestamp":1722581369000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448130\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448130","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}