{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:34:22Z","timestamp":1763202862767,"version":"3.28.0"},"reference-count":24,"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\/icassp48485.2024.10448394","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10021-10025","source":"Crossref","is-referenced-by-count":7,"title":["GEmo-CLAP: Gender-Attribute-Enhanced Contrastive Language-Audio Pretraining for Accurate Speech Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Yu","family":"Pan","sequence":"first","affiliation":[{"name":"Kyushu University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanni","family":"Hu","sequence":"additional","affiliation":[{"name":"Ximalaya Inc.,ShangHai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuguang","family":"Yang","sequence":"additional","affiliation":[{"name":"Ximalaya Inc.,ShangHai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen","family":"Fei","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jixun","family":"Yao","sequence":"additional","affiliation":[{"name":"Ximalaya Inc.,ShangHai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng","family":"Lu","sequence":"additional","affiliation":[{"name":"Ximalaya Inc.,ShangHai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Ma","sequence":"additional","affiliation":[{"name":"University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianjun","family":"Zhao","sequence":"additional","affiliation":[{"name":"Kyushu University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2966857"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746679"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096370"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-703"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095036"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747870"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747460"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3606039.3613109"},{"key":"ref9","first-page":"12449","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":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"article-title":"Roberta: A robustly optimized bert pretraining approach","year":"2019","author":"Liu","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref14","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"International Conference on Machine Learning","author":"Baevski"},{"article-title":"Msac: Multiple speech attribute control method for reliable speech emotion recognition","year":"2023","author":"Pan","key":"ref15"},{"key":"ref16","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11275"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746598"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096586"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095798"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-2271"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2594"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","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\/10448394.pdf?arnumber=10448394","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:53:14Z","timestamp":1722660794000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448394\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448394","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}