{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T00:42:53Z","timestamp":1775090573067,"version":"3.50.1"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054337","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T16:21:13Z","timestamp":1586449273000},"page":"6704-6708","source":"Crossref","is-referenced-by-count":29,"title":["Improving Prosody with Linguistic and Bert Derived Features in Multi-Speaker Based Mandarin Chinese Neural TTS"],"prefix":"10.1109","author":[{"given":"Yujia","family":"Xiao","sequence":"first","affiliation":[]},{"given":"Lei","family":"He","sequence":"additional","affiliation":[]},{"given":"Huaiping","family":"Ming","sequence":"additional","affiliation":[]},{"given":"Frank K.","family":"Soong","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-134"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"4006","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref12","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","author":"arik","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"1118","DOI":"10.21437\/Interspeech.2017-314","article-title":"Speaker-dependent WaveNet vocoder","author":"tamamori","year":"2017","journal-title":"InterSpeech"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref15","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref16","article-title":"Modeling Multi-speaker Latent Space to Improve Neural TTS: Quick Enrolling New Speaker and Enhancing Premium Voice","author":"deng","year":"2018","journal-title":"arXiv preprint arXiv 1812 02588"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682368"},{"key":"ref18","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv preprint arXiv 1810 04805"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3177"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2359987"},{"key":"ref3","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"2013","journal-title":"Proc ICASSP"},{"key":"ref6","article-title":"Char2wav: End-to-end speech synthesis","author":"sotelo","year":"2017","journal-title":"Proc ICLR Workshop"},{"key":"ref5","first-page":"195","article-title":"Deep voice: Real-time neural text-to-speech","volume":"70","author":"arik","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"key":"ref8","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc NIPS"},{"key":"ref7","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc ICLR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367298"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref1","author":"taylor","year":"0","journal-title":"Text-to-Speech Synthesis"},{"key":"ref20","article-title":"Towards Transfer Learning for End-to-End Speech Synthesis from Deep Pre-Trained Language Models","author":"wei","year":"2019","journal-title":"arXiv preprint arXiv 1906 03008"},{"key":"ref22","year":"0"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1511"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5505"},{"key":"ref23","article-title":"Portuguese Named Entity Recognition using BERT-CRF","author":"souza","year":"2019","journal-title":"arXiv preprint arXiv 1909 11324"},{"key":"ref25","article-title":"Feature reinforcement with word embedding and parsing information in neural TTS","author":"ming","year":"2019","journal-title":"arXiv preprint arXiv 1901 04217"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054337.pdf?arnumber=9054337","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:15:47Z","timestamp":1656360947000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054337\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054337","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}