{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T22:41:38Z","timestamp":1757544098183,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413969","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"5704-5708","source":"Crossref","is-referenced-by-count":2,"title":["A New High Quality Trajectory Tiling Based Hybrid TTS In Real Time"],"prefix":"10.1109","author":[{"given":"Feng-Long","family":"Xie","sequence":"first","affiliation":[]},{"given":"Xin-Hui","family":"Li","sequence":"additional","affiliation":[]},{"given":"Wen-Chao","family":"Su","sequence":"additional","affiliation":[]},{"given":"Li","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Frank K.","family":"Soong","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"WaveNet: A generative model for raw audio","year":"2016","author":"van den oord","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3177"},{"key":"ref12","first-page":"6704","article-title":"Improving prosody with linguistic and BERT derived features in multi-speaker based mandarin Chinese neurall TTS","author":"xiao","year":"2020","journal-title":"Proc ICASSP"},{"key":"ref13","first-page":"2410","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"Proc ICML"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2221460"},{"key":"ref17","article-title":"The USTC system for Blizzard Challenge 2008","author":"ling","year":"2008","journal-title":"Proc Blizzard Challenge"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472658"},{"key":"ref19","first-page":"3966","article-title":"Unit selection with hierarchical cascade long short term mem\\ory bidirectional recurrent neural nets","author":"pollet","year":"2017","journal-title":"Proc Inter-speech"},{"key":"ref4","first-page":"8012","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"2013","journal-title":"Proc ICASSP"},{"key":"ref3","first-page":"2347","article-title":"Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis","author":"yoshimura","year":"1999","journal-title":"Proc EUROSPEECH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178816"},{"key":"ref5","first-page":"1964","article-title":"TTS Synthesis with bidirectional LSTM based recurrent neural networks","author":"fan","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref7","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1016\/j.specom.2009.04.004","article-title":"Statistical parametric speech synthesis","volume":"51","author":"zen","year":"2009","journal-title":"Speech Communication"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"1143","DOI":"10.21437\/Interspeech.2017-1107","article-title":"Google’s next-generation real-time unit selection synthesizer using sequence-to-sequence LSTM-based autoencoders","author":"wan","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref22","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053812"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495150"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1008"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413969.pdf?arnumber=9413969","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:03Z","timestamp":1652197263000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413969\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413969","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}