{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T19:05:16Z","timestamp":1768417516131,"version":"3.49.0"},"reference-count":32,"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\/icassp40776.2020.9054107","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7649-7653","source":"Crossref","is-referenced-by-count":15,"title":["Breathing and Speech Planning in Spontaneous Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Eva","family":"Szekely","sequence":"first","affiliation":[]},{"given":"Gustav Eje","family":"Henter","sequence":"additional","affiliation":[]},{"given":"Jonas","family":"Beskow","sequence":"additional","affiliation":[]},{"given":"Joakim","family":"Gustafson","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.5334\/jors.187"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4507"},{"key":"ref30","article-title":"The LJ Speech Dataset","author":"ito","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1044\/jshr.3901.93"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2014-110"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2018-75"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/002383096500800405"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"2218","DOI":"10.21437\/Interspeech.2012-591","article-title":"Pauses and respiratory markers of the structure of book reading","author":"bailly","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2836"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-18"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref18","first-page":"979","article-title":"Bandwidth extension of telephone speech using a filter bank implementation for highband mel spectrum","author":"pulakka","year":"2010","journal-title":"Proc EUSIPCO"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683846"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-419"},{"key":"ref27","article-title":"Tacotron-2 Tensorflow implementation","author":"mama","year":"2018"},{"key":"ref3","first-page":"1","article-title":"Automatic detection of inhalation breath pauses for improved pause modelling in HMM- TTS","volume":"8","author":"braunschweiler","year":"2013","journal-title":"Proc of SSW6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/VHCIE.2019.8714737"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1121\/1.411875"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1044\/jshr.3703.535"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2017.00708"},{"key":"ref2","first-page":"96:1","article-title":"A model for varying speaking style in TTS systems","author":"roekhaut","year":"2010","journal-title":"Proc Speech Prosody"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1159\/000316976"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"1221","DOI":"10.21437\/Eurospeech.2003-392","article-title":"An empirical text transformation method for spontaneous speech synthesizers","author":"sundaram","year":"2003","journal-title":"Proc EUROSPEECH"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760128018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288941"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2165280"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3267851.3267898"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-44"},{"key":"ref26","article-title":"Gentle forced aligner","author":"ochshorn","year":"2017"},{"key":"ref25","article-title":"Google Cloud Speech API video model","year":"0"}],"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\/09054107.pdf?arnumber=9054107","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T19:27:42Z","timestamp":1696015662000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054107\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054107","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}