{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:25:17Z","timestamp":1775229917866,"version":"3.50.1"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,11]],"date-time":"2022-12-11T00:00:00Z","timestamp":1670716800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,11]],"date-time":"2022-12-11T00:00:00Z","timestamp":1670716800000},"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":[[2022,12,11]]},"DOI":"10.1109\/iscslp57327.2022.10037914","type":"proceedings-article","created":{"date-parts":[[2023,2,8]],"date-time":"2023-02-08T18:53:24Z","timestamp":1675882404000},"page":"76-80","source":"Crossref","is-referenced-by-count":3,"title":["AccentSpeech: Learning Accent from Crowd-sourced Data for Target Speaker TTS with Accents"],"prefix":"10.1109","author":[{"given":"Yongmao","family":"Zhang","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":"Zhichao","family":"Wang","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":"Peiji","family":"Yang","sequence":"additional","affiliation":[{"name":"Tencent,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongshen","family":"Sun","sequence":"additional","affiliation":[{"name":"Tencent,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhisheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent,Shenzhen,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":"A survey on neural speech synthesis","volume":"abs\/2106.15561","author":"Tan","year":"2021","journal-title":"CoRR"},{"key":"ref2","first-page":"5167","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, July 10-15, 2018, ser. Proceedings of Machine Learning Research","volume":"80","author":"Wang"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003859"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362069"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383524"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855134"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.11.004"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462258"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053797"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2304637"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746858"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747319"},{"key":"ref15","article-title":"Kespeech: An open source speech dataset of mandarin and its eight subdialects","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, NeurIPS Datasets and Benchmarks 2021","volume":"2021","author":"Tang"},{"key":"ref16","first-page":"3165","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019","volume":"2019","author":"Ren"},{"key":"ref17","first-page":"4700","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, July 10-15, 2018, ser. Proceedings of Machine Learning Research","volume":"80","author":"Skerry-Ryan"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref19","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020","author":"Kong"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3025410"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2530"},{"issue":"CONF","key":"ref22","article-title":"The kaldi speech recognition toolkit","volume-title":"IEEE 2011 workshop on automatic speech recognition and understanding","author":"Povey"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1983"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9746682"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2650"}],"event":{"name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,12,11]]},"end":{"date-parts":[[2022,12,14]]}},"container-title":["2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10037756\/10037573\/10037914.pdf?arnumber=10037914","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T13:58:00Z","timestamp":1707832680000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10037914\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,11]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/iscslp57327.2022.10037914","relation":{},"subject":[],"published":{"date-parts":[[2022,12,11]]}}}