{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T07:37:17Z","timestamp":1725608237433},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,24]],"date-time":"2021-01-24T00:00:00Z","timestamp":1611446400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,24]],"date-time":"2021-01-24T00:00:00Z","timestamp":1611446400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,24]],"date-time":"2021-01-24T00:00:00Z","timestamp":1611446400000},"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":[[2021,1,24]]},"DOI":"10.1109\/iscslp49672.2021.9362077","type":"proceedings-article","created":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T23:37:05Z","timestamp":1614641825000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Exploring Cross-lingual Singing Voice Synthesis Using Speech Data"],"prefix":"10.1109","author":[{"given":"Yuewen","family":"Cao","sequence":"first","affiliation":[]},{"given":"Songxiang","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Shiyin","family":"Kang","sequence":"additional","affiliation":[]},{"given":"Na","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Peng","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Xunying","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Dan","family":"Su","sequence":"additional","affiliation":[]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1109"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054636"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054707"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054556"},{"article-title":"Learning singing from speech","year":"2019","author":"zhang","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853599"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403249"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682674"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683519"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2668"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2201473"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053811"},{"key":"ref27","article-title":"An analysis of phonetic differences between german singing and speaking voices","author":"rosenau","year":"1999","journal-title":"Int Congr Phonetic Sci"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1722"},{"article-title":"Bytesing: A chinese singing voice synthesis system using duration allocated encoder-decoder acoustic models and wavernn vocoders","year":"2020","author":"gu","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053944"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8903099"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1410"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1563"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682656"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/app7121313"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511816338"},{"article-title":"Durian: Duration informed attention network for multimodal synthesis","year":"2019","author":"yu","key":"ref22"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"InterSpeech"},{"key":"ref24","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit","author":"christophe","year":"2016","journal-title":"The Centre for Speech Technology Research (CSTR)"},{"key":"ref23","article-title":"Natural tts synthesis by conditioning wavenet on mel spectrogram pre-dictions","author":"shen","year":"2018","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref26","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"International Conference on Machine Learning"},{"year":"0","key":"ref25","article-title":"Musicxml definition"}],"event":{"name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2021,1,24]]},"location":"Hong Kong","end":{"date-parts":[[2021,1,27]]}},"container-title":["2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9362048\/9362049\/09362077.pdf?arnumber=9362077","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:56Z","timestamp":1652197316000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9362077\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,24]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/iscslp49672.2021.9362077","relation":{},"subject":[],"published":{"date-parts":[[2021,1,24]]}}}