{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:18:20Z","timestamp":1776889100926,"version":"3.51.2"},"reference-count":25,"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\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100003536","name":"Youth Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100003536","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008845","name":"Xinjiang University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008845","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\/icassp48485.2024.10446186","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10101-10105","source":"Crossref","is-referenced-by-count":6,"title":["Improving Speech Emotion Recognition with Unsupervised Speaking Style Transfer"],"prefix":"10.1109","author":[{"given":"Leyuan","family":"Qu","sequence":"first","affiliation":[{"name":"Zhejiang Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"Xinjiang University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cornelius","family":"Weber","sequence":"additional","affiliation":[{"name":"University of Hamburg,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengcheng","family":"Yue","sequence":"additional","affiliation":[{"name":"Zhejiang Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taihao","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Wermter","sequence":"additional","affiliation":[{"name":"University of Hamburg,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/s21041249"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref4","first-page":"21","article-title":"Vocal tract length perturbation (VTLP) improves speech recognition","volume-title":"Proc. ICML Workshop on Deep Learning for Audio, Speech and Language","volume":"117","author":"Jaitly"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054579"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2293"},{"key":"ref8","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"ICML","author":"Wang"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/9781118706664"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593571"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref14","first-page":"577","article-title":"Attention-based models for speech recognition","author":"Chorowski","year":"2015","journal-title":"NeurIPS"},{"key":"ref15","first-page":"17022","article-title":"Hifi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"NeurIPS"},{"key":"ref16","author":"Afouras","year":"2018","journal-title":"LRS3-TED: a large-scale dataset for visual speech recognition"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414006"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2822"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747095"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-33"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415077"},{"key":"ref23","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","volume":"162","author":"Baevski"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/SMM.2018-5"}],"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\/10446186.pdf?arnumber=10446186","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:05:52Z","timestamp":1722575152000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446186\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446186","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}