{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:13:06Z","timestamp":1753600386712,"version":"3.28.0"},"reference-count":20,"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\/icassp40776.2020.9054560","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T16:21:13Z","timestamp":1586449273000},"page":"6684-6688","source":"Crossref","is-referenced-by-count":5,"title":["Scalable Multilingual Frontend for TTS"],"prefix":"10.1109","author":[{"given":"Alistair","family":"Conkie","sequence":"first","affiliation":[]},{"given":"Andrew","family":"Finch","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Char2wav: End-to-end speech synthesis","author":"sotelo","year":"2017","journal-title":"ICLRE"},{"key":"ref11","article-title":"RNN approaches to text normalization: A challenge","volume":"abs 1611 68","author":"sproat","year":"2016","journal-title":"CoRR"},{"key":"ref12","first-page":"2784","article-title":"A mostly data-driven approach to inverse text normalization","author":"pusateri","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-018-9521-x"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-2024"},{"article-title":"Pragmatica and intonation","year":"2008","author":"hirschberg","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref17","article-title":"Attention is all you need","volume":"abs 1706 3762","author":"vaswani","year":"2017","journal-title":"CoRR"},{"key":"ref18","article-title":"Neural machine translation of rare words with subword units","volume":"abs 1508 7909","author":"sennrich","year":"2015","journal-title":"CoRR"},{"key":"ref19","first-page":"311","author":"papineni","year":"2002","journal-title":"BLEU A method for automatic evaluation of machine translation"},{"journal-title":"Multilingual Text-to-Speech Synthesis The Bell Labs Approach","year":"1997","author":"sproat","key":"ref4"},{"article-title":"Language-universal and language-specific components in the multi-language eti-eloquence text-to-speech system","year":"1999","author":"hertz","key":"ref3"},{"key":"ref6","first-page":"61","author":"roark","year":"2012","journal-title":"The openGrm open-source finite-state grammar software libraries"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607867"},{"key":"ref8","article-title":"Natural TTS synthesis by conditioning wavenet on mel spectrogram predictions","volume":"abs 1712 5884","author":"shen","year":"2017","journal-title":"CoRR"},{"key":"ref7","article-title":"Tacotron: A fully end-to-end text-to-speech synthesis model","volume":"abs 1703 10135","author":"wang","year":"2017","journal-title":"CoRR"},{"key":"ref2","article-title":"WaveNet: A generative model for raw audio","volume":"abs 1609 3499","author":"den oord","year":"2016","journal-title":"CoRR"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511816338"},{"key":"ref9","article-title":"Deep voice: Real-time neural text-to-speech","volume":"abs 1702 7825","author":"arik","year":"2017","journal-title":"CoRR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-3049"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","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\/09054560.pdf?arnumber=9054560","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:10:27Z","timestamp":1656360627000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054560\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054560","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}