{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:24:38Z","timestamp":1775229878808,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389638","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-8","source":"Crossref","is-referenced-by-count":6,"title":["Zero-Shot Emotion Transfer for Cross-Lingual Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Yuke","family":"Li","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinfa","family":"Zhu","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Lei","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hai","family":"Li","sequence":"additional","affiliation":[{"name":"iQIYI Inc.,Chengdu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junhui","family":"Liu","sequence":"additional","affiliation":[{"name":"iQIYI Inc.,Chengdu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danming","family":"Xie","sequence":"additional","affiliation":[{"name":"iQIYI Inc.,Chengdu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Delightfultts: The microsoft speech synthesis system for blizzard challenge 2021","volume":"abs\/2110.12612","author":"Liu","year":"2021","journal-title":"CoRR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-349"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511816338"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref5","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020","journal-title":"Proc.ICLR 2021"},{"key":"ref6","article-title":"Adaspeech: Adaptive text to speech for custom voice","author":"Chen","year":"2021","journal-title":"Proc.ICLR 2021"},{"key":"ref7","article-title":"Generspeech: Towards style transfer for generalizable out-of-domain text-to-speech synthesis","volume":"abs\/2205.07211","author":"Huang","year":"2022","journal-title":"CoRR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/chinsl.2008.ecp.14"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1632"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"ref11","article-title":"Accented text-to-speech synthesis with limited data","author":"Zhou","year":"2023","journal-title":"arXiv preprint arXiv:2305.04816"},{"key":"ref12","first-page":"233","article-title":"Second language speech learning: Theory, findings, and problems","volume":"92","author":"Flege","year":"1995","journal-title":"Speech perception and linguistic experience: Issues in cross-language research"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/2387.003.0011"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688137"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2668"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2679"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414226"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096929"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1821"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003859"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3268571"},{"key":"ref26","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Proc.ICML","author":"Wang"},{"key":"ref27","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"Proc.ICLR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145293"},{"key":"ref29","article-title":"Joint multi-scale cross-lingual speaking style transfer with bidirectional attention mechanism for automatic dubbing","volume":"abs\/2305.05203","author":"Li","year":"2023","journal-title":"CoRR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-947"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2786"},{"key":"ref32","first-page":"17022","article-title":"Hifigan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-703"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383456"},{"key":"ref35","first-page":"7748","article-title":"Meta-stylespeech: Multi-speaker adaptive text-to-speech generation","volume-title":"International Conference on Machine Learning","author":"Min"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.nlposs-1.4"},{"key":"ref37","article-title":"Cross-speaker emotion transfer based on speaker condition layer normalization and semi-supervised training in text-to-speech","volume":"abs\/2110.04153","author":"Wu","year":"2021","journal-title":"CoRR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1265"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref40","article-title":"Scaling speech technology to 1,000+ languages","volume":"abs\/2305.13516","author":"Pratap","year":"2023","journal-title":"CoRR"},{"key":"ref41","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,12,16]]},"end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389638.pdf?arnumber=10389638","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:35:40Z","timestamp":1706027740000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389638\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389638","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}