{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T20:15:13Z","timestamp":1771964113901,"version":"3.50.1"},"reference-count":25,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.23919\/apsipa.2018.8659668","type":"proceedings-article","created":{"date-parts":[[2019,3,18]],"date-time":"2019-03-18T19:11:49Z","timestamp":1552936309000},"page":"1702-1707","source":"Crossref","is-referenced-by-count":6,"title":["A DNN-based Mandarin-Tibetan cross-lingual speech synthesis"],"prefix":"10.23919","author":[{"given":"Weitong","family":"Guo","sequence":"first","affiliation":[]},{"given":"Hongwu","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Zhenye","family":"Gan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854318"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178814"},{"key":"ref12","author":"potard","year":"2015","journal-title":"Preliminary work on speaker adaptation for DNN-based speech synthesis"},{"key":"ref13","first-page":"5135","article-title":"Unsupervised speaker adaptation for dnn-based tts synthesis","author":"fan","year":"2016","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref14","article-title":"A study of speaker adaptation for dnn-based speech synthesis","author":"wu","year":"2015","journal-title":"Proceedings Interspeech"},{"key":"ref15","first-page":"1956","article-title":"A training method of average voice model for HMM-based speech synthesis","volume":"e86 a","author":"yamagishi","year":"2003","journal-title":"IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences"},{"key":"ref16","first-page":"186","article-title":"Speaker and language adaptive training for HMM-based polyglot speech synthesis","author":"zen","year":"2010","journal-title":"INTERSPEECH 2010"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"528","DOI":"10.21437\/Interspeech.2009-192","article-title":"State mapping based method for cross-lingual speaker adaptation in HMM-based speech synthesis","author":"wu","year":"2009","journal-title":"INTERSPEECH 2009"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICINFA.2010.5512462"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-014-2117-9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CHINSL.2008.ECP.75"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1016\/S1007-0214(09)70127-0","article-title":"A unified framework for multilingual text-to-speech synthesis with ssml specification as interface","volume":"14","author":"wu","year":"2009","journal-title":"Tsinghua Science and Technology"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"7962","DOI":"10.1109\/ICASSP.2013.6639215","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"2013","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref8","first-page":"261","article-title":"Combining a vector space representation of linguistic context with a deep neural network for text-to-speech synthesis","author":"lu","year":"2013","journal-title":"Proc \/SCA SSW8"},{"key":"ref7","first-page":"75","article-title":"Title research on deep neural network based chinese speech synthesis","volume":"42","author":"wang","year":"2015","journal-title":"Computer Science"},{"key":"ref2","article-title":"Introduction to multilingual corpus-based concatenative speech synthesis","author":"deprez","year":"2007","journal-title":"Eighth Annual Conference of the International Speech Communication Association"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638996"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s12046-011-0050-4"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1111\/j.1749-818X.2008.00061.x"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820818"},{"key":"ref24","author":"mirjam","year":"2010","journal-title":"The EMIME Bilingual Database"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1561\/2000000039"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1007\/978-3-642-19551-8_23","author":"loizou","year":"2011","journal-title":"Speech quality assessment chapter Multimedia analysis processing and communications"}],"event":{"name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","location":"Honolulu, HI, USA","start":{"date-parts":[[2018,11,12]]},"end":{"date-parts":[[2018,11,15]]}},"container-title":["2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8648538\/8659446\/08659668.pdf?arnumber=8659668","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,14]],"date-time":"2023-09-14T12:47:27Z","timestamp":1694695647000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8659668\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":25,"URL":"https:\/\/doi.org\/10.23919\/apsipa.2018.8659668","relation":{},"subject":[],"published":{"date-parts":[[2018,11]]}}}