{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T03:38:08Z","timestamp":1752982688175,"version":"3.28.0"},"reference-count":23,"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\/icassp48485.2024.10446112","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"461-465","source":"Crossref","is-referenced-by-count":1,"title":["Fastmandarin: Efficient Local Modeling for Natural Mandarin Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Chenglong","family":"Jiang","sequence":"first","affiliation":[{"name":"South China University of Technology,School of Computer and Engineering,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Gao","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Computer and Engineering,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Jin","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Computer and Engineering,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linrong","family":"Pan","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Computer and Engineering,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wing W. Y.","family":"Ng","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Computer and Engineering,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/ICASSP.2014.6854318"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/ICASSP.2015.7178816"},{"key":"ref3","article-title":"Sequence to sequence learning with neural networks","volume-title":"Advances in neural information processing systems","volume":"27","author":"Sutskever"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.21437\/Interspeech.2016-134"},{"year":"2017","author":"Sotelo","journal-title":"Char2wav: End-to-end speech synthesis","key":"ref5"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.21437\/Interspeech.2017-1452"},{"year":"2017","author":"Ping","journal-title":"Deep voice 3: 2000-speaker neural text-to-speech","key":"ref7"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.48550\/ARXIV.1706.03762"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1609\/aaai.v33i01.33016706"},{"year":"2020","author":"Ren","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","key":"ref10"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.18653\/v1\/D18-1475"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1016\/j.neunet.2020.01.034"},{"key":"ref13","first-page":"340","article-title":"Joint chinese word segmentation and part-of-speech tagging via two-stage span labeling","volume-title":"Proceedings of the 35th Pacific Asia Conference on Language, Information and Computation","author":"Nguyen"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/ICASSP40776.2020.9053390"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.21437\/Interspeech.2019-1118"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/5.18626"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/PROC.1973.9030"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/ASRU46091.2019.9003949"},{"key":"ref19","first-page":"933","article-title":"Language modeling with gated convolutional networks","volume-title":"International conference on machine learning","author":"Dauphin"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref21","first-page":"17022","article-title":"Hifigan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Kong"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1121\/1.1458024"},{"key":"ref23","first-page":"276","article-title":"A kernelized stein discrepancy for goodness-of-fit tests","volume-title":"Proceedings of The 33rd International Conference on Machine Learning","volume":"48","author":"Liu"}],"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\/10446112.pdf?arnumber=10446112","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:02:49Z","timestamp":1722574969000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446112\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446112","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}