{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T17:46:09Z","timestamp":1775497569597,"version":"3.50.1"},"reference-count":43,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10445906","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T14:56:31Z","timestamp":1710773791000},"page":"11146-11150","source":"Crossref","is-referenced-by-count":28,"title":["Leveraging Speech PTM, Text LLM, And Emotional TTS For Speech Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Ziyang","family":"Ma","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Cambridge,Department of Engineering,Cambridge,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhisheng","family":"Zheng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiwei","family":"Guo","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab of DAMO Academy,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiliang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab of DAMO Academy,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xie","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2021.3114365"},{"key":"ref2","article-title":"SUPPERB: Speech processing universal performance benchmark","volume-title":"Proc. of Interspeech","author":"Yang"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref5","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","volume-title":"Proc. of ICLR","author":"Baevski"},{"key":"ref6","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. of NeurIPS","author":"Baevski"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref9","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. of ICML","author":"Baevski"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-822"},{"key":"ref11","article-title":"Tessp: text-enhanced self-supervised speech pretraining","author":"Yao","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-791"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-630"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1176"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747814"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-293"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-703"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1109\/SLT54892.2023.10023428","article-title":"Exploration of a self-supervised speech model: A study on emotional corpora","volume-title":"Proc. of SLT","author":"Li"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9747870"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095036"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747460"},{"key":"ref22","article-title":"A fine-tuned wav2vec 2.0\/hubert benchmark for speech emotion recognition, speaker verification and spoken language understanding","author":"Wang","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-497"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2024.3369726"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref28","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. of ICLR","author":"Zhang"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3252"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593571"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2022.3221749"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3190"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054317"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3390\/s22165941"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2293"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054579"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1080"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/tcss.2024.3396345"},{"key":"ref39","volume-title":"GPT-4 technical report","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095621"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(96)00068-4"},{"key":"ref43","article-title":"Domain-adversarial training of neural networks","author":"Ganin","year":"2016","journal-title":"J. of JMLR"}],"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\/10445906.pdf?arnumber=10445906","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T04:33:30Z","timestamp":1769488410000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10445906\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10445906","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}