{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:14:07Z","timestamp":1740132847681,"version":"3.37.3"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2019YFB1312603"],"award-info":[{"award-number":["2019YFB1312603"]}]},{"name":"Robotics Institute of Zhejiang University","award":["K11801"],"award-info":[{"award-number":["K11801"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/lsp.2023.3256319","type":"journal-article","created":{"date-parts":[[2023,3,13]],"date-time":"2023-03-13T18:11:01Z","timestamp":1678731061000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Mandarin Text-to-Speech Front-End with Lightweight Distilled Convolution Network"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8452-9339","authenticated-orcid":false,"given":"Wei","family":"Zhao","sequence":"first","affiliation":[{"name":"College of Electrical Engineering, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7652-268X","authenticated-orcid":false,"given":"Zuyi","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Electrical Engineering, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7874-629X","authenticated-orcid":false,"given":"Li","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Electrical Engineering, Zhejiang University, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2292"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3124365"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003918"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1418"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref11","first-page":"5753","article-title":"Generalized autoregressive pretraining for language understanding","author":"yang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"article-title":"Robustly optimized BERT pretraining approach","year":"2019","author":"liu","key":"ref10"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2012.6423468"},{"key":"ref1","first-page":"165","article-title":"Grapheme-to-phoneme conversion in chinese TTS system","author":"dong","year":"0","journal-title":"Proc IEEE Int Symp Chin Spoken Lang Process"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref16","article-title":"Pay less attention with lightweight and dynamic convolutions","author":"wu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","year":"2020","author":"sanh","key":"ref18"},{"key":"ref24","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref23","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","author":"lan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"article-title":"Unified mandarin TTS front-end based on distilled BERT model","year":"2020","author":"zhang","key":"ref26"},{"key":"ref25","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1094"},{"key":"ref22","first-page":"12837","article-title":"ConvBERT: Improving BERT with span-based dynamic convolution","author":"jiang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-755"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1441"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref29","first-page":"3171","article-title":"FastSpeech: Fast, robust and controllable text to speech","author":"ren","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1472"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1400"},{"key":"ref9","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proc Annu Conf North Amer Chapter Assoc Comput Linguistics"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367010"},{"key":"ref3","first-page":"4657","article-title":"Tree-guided transformation-based homograph disambiguation in mandarin TTS system","author":"liu","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2016.7918392"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2010.5684835"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/4358004\/10068234.pdf?arnumber=10068234","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T14:52:39Z","timestamp":1679928759000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10068234\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/lsp.2023.3256319","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"type":"print","value":"1070-9908"},{"type":"electronic","value":"1558-2361"}],"subject":[],"published":{"date-parts":[[2023]]}}}