{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T15:38:11Z","timestamp":1779118691510,"version":"3.51.4"},"reference-count":24,"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\/icassp40776.2020.9054319","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T16:21:13Z","timestamp":1586449273000},"page":"6709-6713","source":"Crossref","is-referenced-by-count":4,"title":["Focusing on Attention: Prosody Transfer and Adaptative Optimization Strategy for Multi-Speaker End-to-End Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Ruibo","family":"Fu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengqi","family":"Wen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangyan","family":"Yi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-134"},{"key":"ref11","article-title":"Char2Wav: End-to-end speech synthesis","author":"sotelo","year":"2017","journal-title":"Proceedings of ICLR workshop submission"},{"key":"ref12","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc NIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1972"},{"key":"ref15","first-page":"4700","article-title":"Towards end- to-end prosody transfer for expressive speech synthesis with Tacotron","author":"skerry-ryan","year":"2018","journal-title":"Proceedings ICML 2018-Proceedings of the 35th International Conference on Machine Learning"},{"key":"ref16","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to- end speech synthesis","author":"wang","year":"2018","journal-title":"Proceedings ICML 2018- Proceedings of the 35th International Conference on Machine Learning"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639682"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1021\/i200032a041"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref4","article-title":"WaveNet: A Generative Model for Raw Audio","author":"oord","year":"2017","journal-title":"Proceedings of the Annual Conference of the International Speech Communication Association INTERSPEECH 2017"},{"key":"ref3","article-title":"Close to human quality TTS with transformer","author":"li","year":"2018","journal-title":"arXiv preprint arXiv 1809 08895"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref5","article-title":"Neural Machine Translation by Jointly Learning to Align and Translate","author":"bahdanau","year":"2014","journal-title":"arXiv preprint arXiv 1409 0473"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref7","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"IEEE International Conference on Machine Learning ICML 2015"},{"key":"ref2","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","author":"ping","year":"2018","journal-title":"ICLR 2018? International Conference on Learning Representations 2018"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref9","article-title":"Generating sequences with recurrent neural networks","author":"graves","year":"2013","journal-title":"arXiv preprint arXiv 1308 0850"},{"key":"ref20","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":"ref22","author":"moore","year":"2012","journal-title":"An Introduction to the Psychology of Hearing"},{"key":"ref21","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref24","article-title":"On the convergence of adam and beyond","author":"reddi","year":"2018","journal-title":"ICLR 2018? International Conference on Learning Representations 2018"},{"key":"ref23","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proceedings of the 2015 International Conference on Learning Representations"}],"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\/09054319.pdf?arnumber=9054319","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:18:54Z","timestamp":1656361134000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054319\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054319","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}