{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:27:11Z","timestamp":1775230031308,"version":"3.50.1"},"reference-count":28,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383591","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T20:46:54Z","timestamp":1616705214000},"page":"431-437","source":"Crossref","is-referenced-by-count":9,"title":["Supervised and unsupervised approaches for controlling narrow lexical focus in sequence-to-sequence speech synthesis"],"prefix":"10.1109","author":[{"given":"Slava","family":"Shechtman","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raul","family":"Fernandez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Haws","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"34","article-title":"Automatic exploration of corpus-specific properties for expressive text-to-speech: A case study in emphasis","author":"fernandez","year":"2007","journal-title":"Proc SSW6"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"1282","DOI":"10.21437\/Interspeech.2007-230","article-title":"Modeling prominence and emphasis improves unit-selection synthesis","author":"strom","year":"2007","journal-title":"Proc INTERSPEECH"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495690"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"466","DOI":"10.21437\/Interspeech.2012-159","article-title":"Hierarchical english emphatic speech synthesis based on HMM with limited training data","author":"meng","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-930"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462473"},{"key":"ref16","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume":"abs 1803 9017","author":"wang","year":"2018","journal-title":"CoRR"},{"key":"ref17","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with Tacotron","volume":"abs 1803 9047","author":"skerry-ryan","year":"2018","journal-title":"CoRR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054556"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.876123"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2571"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1159"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-49"},{"key":"ref8","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref7","article-title":"Layer normalization","volume":"abs 1607 6450","author":"ba","year":"2016","journal-title":"CoRR"},{"key":"ref2","article-title":"Controllable sequence-to-sequence neural TTS with LPC-NET backend for real-time speech synthesis on CPU","author":"shechtman","year":"2020","journal-title":"CoRR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2003.1318525"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683827"},{"key":"ref22","first-page":"3171","article-title":"FastSpeech: Fast, robust and controllable Text to Speech","volume":"32","author":"ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003829"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003859"},{"key":"ref23","article-title":"FastSpeech 2: Fast and high-quality end-to-end Text to Speech","author":"ren","year":"2020","journal-title":"CoRR"},{"key":"ref26","first-page":"6264","article-title":"Fully-hierarchichal fine-grained prosody modeling for interpretable speech synthesis","author":"sun","year":"2020","journal-title":"Proc ICASSP"},{"key":"ref25","article-title":"Hierarchical generative modeling for controllable speech synthesis","author":"hsu","year":"2019","journal-title":"Proc ICLR"}],"event":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","location":"Shenzhen, China","start":{"date-parts":[[2021,1,19]]},"end":{"date-parts":[[2021,1,22]]}},"container-title":["2021 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9383468\/9383452\/09383591.pdf?arnumber=9383591","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T21:07:49Z","timestamp":1724706469000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383591\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383591","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}