{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:44:03Z","timestamp":1767339843042,"version":"3.37.3"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11664036"],"award-info":[{"award-number":["11664036"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"High School Science and Technology Innovation Team Project of Gansu","award":["2017C-03"],"award-info":[{"award-number":["2017C-03"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2954342","type":"journal-article","created":{"date-parts":[[2019,11,19]],"date-time":"2019-11-19T15:52:23Z","timestamp":1574178743000},"page":"167884-167894","source":"Crossref","is-referenced-by-count":17,"title":["Deep Learning for Mandarin-Tibetan Cross-Lingual Speech Synthesis"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3692-4921","authenticated-orcid":false,"given":"Weizhao","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8939-3386","authenticated-orcid":false,"given":"Hongwu","family":"Yang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1983-4251","authenticated-orcid":false,"given":"Xiaolong","family":"Bu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2028-7454","authenticated-orcid":false,"given":"Lili","family":"Wang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"The EMIME bilingual database","year":"2010","author":"wester","key":"ref33"},{"key":"ref32","first-page":"41","article-title":"Predicting Chinese prosodic boundary based on syntactic features","volume":"49","author":"yang","year":"2013","journal-title":"J Northwest Normal Univ Natural Sci"},{"key":"ref31","first-page":"282","article-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","author":"lafferty","year":"2001","journal-title":"Proc 18th Int Conf Mach Learn (ICML)"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1030"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2746264"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IAEAC.2017.8054091"},{"key":"ref14","first-page":"2129","article-title":"Introduction to multilingual corpus-based concatenative speech synthesis","author":"deprez","year":"2007","journal-title":"Proc 8th Annu Conf Int Speech Commun Assoc"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S1007-0214(09)70127-0"},{"key":"ref16","first-page":"317","article-title":"Cross-lingual speaker adaptation for statistical speech synthesis using limited data","author":"fan","year":"2016","journal-title":"Proc Annu Conf Int Speech Commun Assoc (Interspeech)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2667880"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-014-2117-9"},{"key":"ref19","first-page":"776","article-title":"Realizing Mandarin-Tibetan bilingual speech synthesis by speaker adaptive training","volume":"53","author":"wang","year":"2013","journal-title":"J Tsinghua Univ Sci Technol"},{"key":"ref28","first-page":"71","article-title":"Study on fusion of unsupervised features for Tibetan word segmentation","volume":"31","author":"li","year":"2017","journal-title":"J Chin Inf Process"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref27","first-page":"132","article-title":"Research on several key issues in Tibetan word segmentation","volume":"28","author":"wanmezhaxi","year":"2014","journal-title":"J Chin Inf Process"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682861"},{"key":"ref29","first-page":"203","article-title":"An open source toolkit for Tibetan word segmentation and POS tagging","volume":"29","author":"li","year":"2015","journal-title":"J Chin Inf Process"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"ref8","first-page":"1","article-title":"On the training of DNN-based average voice model for speech synthesis","author":"yang","year":"2017","journal-title":"Proc Signal Inf Process Assoc Summit Conf"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2359987"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472732"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178817"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s12046-011-0050-4"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472738"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639215"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659668"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref23","first-page":"879","article-title":"A study of speaker adaptation for DNN-based speech synthesis","author":"wu","year":"2015","journal-title":"Proc 16th Annu Conf Int Speech Commun Assoc (INTERSPEECH)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref25","first-page":"1964","article-title":"TTS synthesis with bidirectional LSTM based recurrent neural networks","author":"fan","year":"2014","journal-title":"Proc 15th Annu Conf Int Speech Commun Assoc (INTERSPEECH)"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08906089.pdf?arnumber=8906089","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:32:15Z","timestamp":1641987135000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8906089\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2954342","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2019]]}}}