{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T18:00:33Z","timestamp":1776276033693,"version":"3.50.1"},"reference-count":31,"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\/icassp40776.2020.9053915","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"6729-6733","source":"Crossref","is-referenced-by-count":15,"title":["Transformer-Based Text-to-Speech with Weighted Forced Attention"],"prefix":"10.1109","author":[{"given":"Takuma","family":"Okamoto","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshinori","family":"Shiga","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hisashi","family":"Kawai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref30","year":"1996","journal-title":"ITU-T recommendation P 800 methods for subjective determination of transmission quality"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1288"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682368"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2167"},{"key":"ref14","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003956"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683827"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2914149"},{"key":"ref28","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref4","article-title":"Char2Wav: End-to-end speech synthesis","author":"sotelo","year":"2017","journal-title":"Proc ICLR"},{"key":"ref27","first-page":"2268","article-title":"Prosody contour prediction with long short-term memory, bidirectional, deep recurrent neural networks","author":"fernandez","year":"2014","journal-title":"Proc Inter-speech"},{"key":"ref3","article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","author":"mehri","year":"2017","journal-title":"Proc ICLR"},{"key":"ref6","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","author":"ping","year":"2018","journal-title":"Proc ICLR"},{"key":"ref29","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref5","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":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461829"},{"key":"ref2","first-page":"1118","article-title":"Speaker-dependent WaveNet vocoder","author":"tamamori","year":"2017","journal-title":"Proc In-terspeech"},{"key":"ref9","first-page":"6905","article-title":"Investigation of enhanced Tacotron text-to-speech synthesis systems with self-attention for pitch accent language","author":"yasuda","year":"2019","journal-title":"Proc ICASSP"},{"key":"ref1","first-page":"125","article-title":"WaveNet: A generative model for raw audio","author":"den oord","year":"2016","journal-title":"Proc SSW9"},{"key":"ref20","first-page":"3165","article-title":"FastSpeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-39"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.813579"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1006"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1139"},{"key":"ref26","first-page":"1964","article-title":"TTS synthesis with bidirectional LSTM based recurrent neural networks","author":"fan","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-30"}],"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\/09053915.pdf?arnumber=9053915","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:11:49Z","timestamp":1656375109000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053915\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053915","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}